© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 876
    Prev
    Next
    INDEX
    Explanations

    the verb "hide" in various contexts and forms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1828
    +0.08
    0.3%
    874
    +0.07
    0.3%
    991
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    991
    +0.08
    0.03
    851
    +0.07
    0.03
    1242
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.44
    ⓧ
    -0.74
    <?
    -0.62
    public
    -0.59
    
    -0.58
    <?
    -0.57
    multicolumn
    -0.55
    setViewport
    -0.54
    bibnamefont
    -0.54
    HasColumnType
    -0.53
    POSITIVE LOGITS
     hide
    2.19
     hides
    2.06
     Hide
    2.04
     hiding
    1.99
     Hiding
    1.92
    Hide
    1.85
    hide
    1.79
    Hiding
    1.73
    hiding
    1.71
     hid
    1.53
    Activations Density 0.141%

    No Known Activations