© 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. 91558
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     Италијани
    -0.59
    principalTable
    -0.57
    ImageContext
    -0.56
    cnbc
    -0.52
     initWithFrame
    -0.49
    patine
    -0.49
    出版年
    -0.49
    owieck
    -0.49
    esez
    -0.48
    ņi
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.68
     autorytatywna
    0.68
     Wikiseite
    0.53
     Combien
    0.52
    atid
    0.50
    ISupport
    0.50
    WebControls
    0.49
    ftagPool
    0.49
    EndInit
    0.48
    RectangleBorder
    0.48
    Activations Density 0.004%

    No Known Activations