© 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. 4-CLT-HP
    7. 4385
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ^(@)
    -0.91
    __':
    -0.86
    ſelf
    -0.81
     onAnimation
    -0.78
     виправивши
    -0.77
    BibitemShut
    -0.75
     Forumite
    -0.75
    حياتها
    -0.75
    évaluateur
    -0.74
    intenance
    -0.74
    POSITIVE LOGITS
    I
    0.63
    It
    0.59
    /
    0.58
    "
    0.57
    </b>
    0.55
    My
    0.55
    –
    0.55
    In
    0.54
    is
    0.54
    and
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.