© 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. 0-CLT-HP
    7. 42755
    Prev
    Next
    INDEX
    Explanations

    explosions or growth

    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
    новниш
    -0.98
    ftagPool
    -0.91
     myſelf
    -0.91
    esterday
    -0.89
    fjspx
    -0.88
    GEBURTSDATUM
    -0.88
     ModelExpression
    -0.88
    TemporalType
    -0.88
    Datuak
    -0.87
     Мексичка
    -0.86
    POSITIVE LOGITS
    !
    0.81
    .
    0.79
    ,
    0.75
    ly
    0.72
    ;
    0.66
    '
    0.65
    …
    0.63
    <eos>
    0.62
    :
    0.59
    ’
    0.59
    Activations Density 1.078%

    No Known Activations