© 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. 91310
    Prev
    Next
    INDEX
    Explanations

    time

    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
    AlterField
    -0.51
    CloseOperation
    -0.51
    TagMode
    -0.49
    idste
    -0.49
     JADX
    -0.48
    Begriffsklä
    -0.47
     cump
    -0.46
    STERY
    -0.46
    Ừ
    -0.46
    irsten
    -0.46
    POSITIVE LOGITS
    __":
    0.60
    存于互联网档案馆
    0.60
     where
    0.55
    Портал
    0.53
    ,
    0.50
    Smarty
    0.50
     how
    0.49
    Portály
    0.49
     why
    0.48
    ’
    0.48
    Activations Density 0.023%

    No Known Activations