© 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. 93910
    Prev
    Next
    INDEX
    Explanations

    changes, modifications

    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
     itſelf
    -1.46
     purpoſe
    -1.44
     ſche
    -1.41
     myſelf
    -1.41
     houſe
    -1.38
     pleaſure
    -1.38
     Theſe
    -1.35
     Efq
    -1.34
     ſtate
    -1.33
     Majefty
    -1.30
    POSITIVE LOGITS
    .
    1.06
    ,
    0.98
     and
    0.97
     for
    0.88
     (
    0.87
     of
    0.87
     in
    0.86
     made
    0.85
     that
    0.80
     
    0.74
    Activations Density 0.156%

    No Known Activations