© 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. 95364
    Prev
    Next
    INDEX
    Explanations

    HTML and code fragments

    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
    -1.64
     myſelf
    -1.58
     Efq
    -1.53
     themſelves
    -1.45
    ſelves
    -1.43
     Jefus
    -1.43
    ſelf
    -1.40
     Majefty
    -1.40
     raiſ
    -1.35
     iſt
    -1.34
    POSITIVE LOGITS
    y
    0.75
    i
    0.74
    ي
    0.72
    ,
    0.71
    se
    0.71
    '
    0.69
    m
    0.68
    ?
    0.68
    za
    0.68
    um
    0.67
    Activations Density 0.255%

    No Known Activations