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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10471
    Prev
    Next
    INDEX
    Explanations

    science

    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
    logeny
    -0.79
     kasarigan
    -0.67
     Nae
    -0.62
    NESS
    -0.61
     useDispatch
    -0.61
    NGS
    -0.58
    ness
    -0.56
     ITIS
    -0.54
    monial
    -0.53
    insics
    -0.52
    POSITIVE LOGITS
    <bos>
    0.60
    rès
    0.51
    AndEndTag
    0.50
    RuleContext
    0.50
    Starting
    0.49
     starting
    0.49
    دهم
    0.49
     of
    0.48
     šķ
    0.46
    gång
    0.45
    Activations Density 0.025%

    No Known Activations