© 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. 42763
    Prev
    Next
    INDEX
    Explanations

    New

    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
     New
    -1.84
    New
    -1.63
     NEW
    -1.10
    NEW
    -1.00
     Nueva
    -0.97
     new
    -0.88
    在新
    -0.84
     Nouvelle
    -0.80
     Новый
    -0.79
    new
    -0.78
    POSITIVE LOGITS
     Yorker
    0.82
    extAlignment
    0.81
     Zealand
    0.78
    rawDesc
    0.74
     courants
    0.73
     Majefty
    0.73
     EconPapers
    0.73
    LookAnd
    0.71
     GenerationType
    0.70
    antaranya
    0.69
    Activations Density 0.079%

    No Known Activations