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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 570
    Prev
    Next
    INDEX
    Explanations

    adjectives related to negativity

    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
    120
    +0.10
    0.3%
    1604
    +0.09
    0.3%
    411
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.02
    1205
    +0.09
    0.02
    1896
    +0.09
    0.01
    Negative Logits
     retro
    -0.77
    namespace
    -0.70
    retro
    -0.70
    <bos>
    -0.68
    DoubleQuotes
    -0.67
    IsRequired
    -0.64
    FunctionFlags
    -0.63
    cshtml
    -0.62
    <eos>
    -0.62
    public
    -0.62
    POSITIVE LOGITS
     stockholm
    2.10
     wikihow
    2.05
     Bitter
    2.04
     squa
    1.97
     michelin
    1.96
     bitter
    1.92
     affor
    1.91
     fta
    1.89
     fep
    1.86
     eiffel
    1.86
    Activations Density 0.233%

    No Known Activations