© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2107
    Prev
    Next
    INDEX
    Explanations

    part

    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
     ComVisible
    -0.56
    存于互联网档案馆
    -0.54
     circonstances
    -0.52
     panneaux
    -0.48
    for
    -0.47
    zan
    -0.47
    Phaser
    -0.47
    цездатний
    -0.46
    र्शन
    -0.46
     artesanía
    -0.45
    POSITIVE LOGITS
    !*\
    0.65
     Efq
    0.63
    BufferException
    0.56
     setOpen
    0.56
     visiting
    0.56
     interviewing
    0.56
    aarrggbb
    0.55
     flipping
    0.54
     prosecuting
    0.54
    حوالہ
    0.53
    Activations Density 0.005%

    No Known Activations