© 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. 1-CLT-HP
    7. 9456
    Prev
    Next
    INDEX
    Explanations

    purpose

    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
     purpose
    -1.02
    purpose
    -0.92
    PURPOSE
    -0.75
     Purpose
    -0.74
    Purpose
    -0.73
     PURPOSE
    -0.72
    +#+
    -0.68
    ConstraintMaker
    -0.65
    PointerException
    -0.63
    oyl
    -0.62
    POSITIVE LOGITS
    tagHelperRunner
    0.73
     uova
    0.51
     חיצוניים
    0.50
     délais
    0.49
     myö
    0.49
    assertRaises
    0.49
     endblock
    0.48
     majeure
    0.48
     seguida
    0.47
     Vote
    0.46
    Activations Density 0.014%

    No Known Activations