© 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. 94209
    Prev
    Next
    INDEX
    Explanations

    underserved communities

    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
     score
    -0.89
     offset
    -0.71
     Off
    -0.68
     Score
    -0.67
     kasarigan
    -0.65
     offs
    -0.64
    Personendaten
    -0.61
     Вікіпе
    -0.60
     SCORE
    -0.60
     off
    -0.59
    POSITIVE LOGITS
    cat
    0.65
    str
    0.52
    set
    0.52
    מע
    0.51
    list
    0.51
    sets
    0.51
    pad
    0.51
    bed
    0.50
     verbinding
    0.49
    znac
    0.49
    Activations Density 0.088%

    No Known Activations