© 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. 585
    Prev
    Next
    INDEX
    Explanations

    expressions related to evaluation or assessment with a positive connotation

    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
    50
    +0.08
    0.3%
    313
    +0.07
    0.2%
    484
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.08
    0.03
    1692
    +0.07
    0.03
    1344
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.03
     "..\..\..\
    -0.63
    deinit
    -0.62
    endwhile
    -0.58
    href
    -0.57
    ⓧ
    -0.56
     won
    -0.55
    lateinit
    -0.55
    <?
    -0.54
    public
    -0.54
    POSITIVE LOGITS
     Express
    2.26
     express
    2.23
    Express
    2.21
    express
    2.08
     EXPRESS
    1.91
    EXPRESS
    1.80
     expresses
    1.60
     expressing
    1.55
     wien
    1.50
     espri
    1.49
    Activations Density 0.142%

    No Known Activations