© 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. 98284
    Prev
    Next
    INDEX
    Explanations

    enabled

    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
    ſelf
    -0.94
     myſelf
    -0.90
     itſelf
    -0.90
     pleaſure
    -0.89
     becauſe
    -0.85
     ſtate
    -0.81
    IVEREF
    -0.81
     themſelves
    -0.80
    ScopeManager
    -0.80
     purpoſe
    -0.79
    POSITIVE LOGITS
    SOME
    0.47
    endregion
    0.45
     SOME
    0.42
    queryInterface
    0.42
    リュー
    0.42
     or
    0.41
     worth
    0.40
    OrNil
    0.40
    kla
    0.40
     until
    0.40
    Activations Density 0.009%

    No Known Activations