© 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. 4928
    Prev
    Next
    INDEX
    Explanations

    Intersections and connections

    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
     uſed
    -0.82
    ГЛА
    -0.73
     myſelf
    -0.72
     raiſ
    -0.70
    RectangleBorder
    -0.69
    bibfield
    -0.68
    kyou
    -0.68
     Teut
    -0.68
     themſelves
    -0.67
    Spoljašnje
    -0.66
    POSITIVE LOGITS
     of
    0.65
     where
    0.51
    spunkt
    0.51
    исленность
    0.50
     género
    0.47
    </b>
    0.46
    spunk
    0.44
     with
    0.43
     between
    0.43
    </i>
    0.42
    Activations Density 0.002%

    No Known Activations