© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 92489
    Prev
    Next
    INDEX
    Explanations

    client

    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
    存于互联网档案馆
    -0.90
     autorytatywna
    -0.85
    EndInit
    -0.81
    DockStyle
    -0.79
    SequentialGroup
    -0.79
     ſei
    -0.77
    OGND
    -0.77
    onViewCreated
    -0.76
     FetchType
    -0.76
    NUMX
    -0.75
    POSITIVE LOGITS
     and
    0.87
     however
    0.77
     or
    0.76
     a
    0.74
     but
    0.73
     then
    0.72
     even
    0.70
     here
    0.69
     though
    0.68
     now
    0.66
    Activations Density 0.012%

    No Known Activations