© 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. 92431
    Prev
    Next
    INDEX
    Explanations

    the

    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
    }],
    -0.53
    .*")]
    -0.52
     ModelExpression
    -0.51
     principal
    -0.50
    pitaux
    -0.49
     main
    -0.48
    — 
    -0.48
    AccessorTable
    -0.47
    TagMode
    -0.46
    "</
    -0.46
    POSITIVE LOGITS
    مراجع
    0.73
    rungsseite
    0.66
    qtype
    0.62
    ftagPool
    0.59
     claridad
    0.57
    Active
    0.52
     Biôgrafia
    0.52
     OFDb
    0.51
    fjspx
    0.51
    RenderAtEndOf
    0.50
    Activations Density 0.204%

    No Known Activations