© 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. 98179
    Prev
    Next
    INDEX
    Explanations

    no

    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
    <bos>
    -0.63
    x
    -0.45
    ks
    -0.45
     or
    -0.44
    a
    -0.42
    or
    -0.40
    older
    -0.40
    ち
    -0.40
    é
    -0.38
    la
    -0.37
    POSITIVE LOGITS
    MemoryWarning
    0.78
    CloseOperation
    0.76
    RenderAtEndOf
    0.75
    PerformLayout
    0.75
     Signalez
    0.73
    ]='\
    0.73
    IVEREF
    0.71
    bootstrapcdn
    0.67
    jsdelivr
    0.66
    ChildScrollView
    0.63
    Activations Density 0.003%

    No Known Activations