© 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. 0-CLT-HP
    7. 43357
    Prev
    Next
    INDEX
    Explanations

    trouble

    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
    yntaxException
    -0.79
    AccessorTable
    -0.73
    WriteBarrier
    -0.68
     Colors
    -0.68
    contentLoaded
    -0.67
    QMetaType
    -0.67
    lapsingToolbar
    -0.63
    StructEnd
    -0.63
    LookAnd
    -0.61
     colors
    -0.60
    POSITIVE LOGITS
    <bos>
    0.51
    存于互联网档案馆
    0.51
    NegativeButton
    0.48
    istoitu
    0.45
     MainAxisSize
    0.45
     réputation
    0.43
     Romains
    0.43
    }{*}{}
    0.43
     movimenti
    0.43
     secoli
    0.43
    Activations Density 0.261%

    No Known Activations