© 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. 5-CLT-HP
    7. 5366
    Prev
    Next
    INDEX
    Explanations

    to

    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
     pleaſure
    -0.80
     myſelf
    -0.76
     uſe
    -0.70
     ſtate
    -0.69
    URLException
    -0.66
     beſt
    -0.66
     purpoſe
    -0.66
    LEncoder
    -0.65
    posedge
    -0.65
    aarrggbb
    -0.64
    POSITIVE LOGITS
     Enough
    0.54
     ENOUGH
    0.52
     enough
    0.49
     suficientes
    0.49
     suficiente
    0.49
    Enough
    0.44
     himo
    0.43
    וויק
    0.43
     at
    0.43
     væ
    0.43
    Activations Density 0.002%

    No Known Activations