© 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. 5426
    Prev
    Next
    INDEX
    Explanations

    a

    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
    GOTREF
    -0.82
    /**
    -0.71
    脚注の使い方
    -0.60
    TypedDataSet
    -0.56
    それと
    -0.55
     Tym
    -0.55
    those
    -0.54
    ungsbedingungen
    -0.53
    Jem
    -0.53
     Smaller
    -0.52
    POSITIVE LOGITS
    neurial
    0.53
    VersionUID
    0.52
    RetentionPolicy
    0.51
    DBNull
    0.50
    ècie
    0.50
     few
    0.48
    ImageContext
    0.48
     mañana
    0.46
    odus
    0.46
    jsxFileName
    0.46
    Activations Density 0.004%

    No Known Activations