© 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. Gemma-2-2B
    5. 5-CLT-HP
    7. 96052
    Prev
    Next
    INDEX
    Explanations

    Compared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.60
    ,
    -0.58
    .
    -0.54
    </strong>
    -0.50
    :
    -0.47
    ;
    -0.47
     -
    -0.44
     —
    -0.40
    <eos>
    -0.37
     [
    -0.36
    POSITIVE LOGITS
     '\\;'
    1.01
     Савезне
    0.91
    Бахар
    0.91
    <bos>
    0.90
     nahilalakip
    0.87
     كومونز
    0.86
     للمعارف
    0.84
    المناصب
    0.83
     purpoſe
    0.82
    <?
    0.82
    Activations Density 0.708%

    No Known Activations