© 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. 91683
    Prev
    Next
    INDEX
    Explanations

    Problems or URLs

    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
     MainAxisSize
    -0.73
    go
    -0.52
    vanju
    -0.47
     שוליים
    -0.44
     besoin
    -0.43
    Go
    -0.43
    origine
    -0.42
     besky
    -0.42
     faixa
    -0.42
     tetapi
    -0.42
    POSITIVE LOGITS
    ConstraintMaker
    0.74
    Personendaten
    0.73
    VIAF
    0.71
     pleaſure
    0.63
    InjectAttribute
    0.63
    تقاوى
    0.60
     ſever
    0.60
     uſ
    0.59
     continúas
    0.59
    WebElementEntity
    0.59
    Activations Density 0.000%

    No Known Activations