© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41399
    Prev
    Next
    INDEX
    Explanations

    Einstein

    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
     Morris
    -0.96
     soul
    -0.93
    Morris
    -0.83
    Einstein
    -0.76
     Einstein
    -0.71
     MORRIS
    -0.70
     morris
    -0.70
     Soul
    -0.61
     Palmer
    -0.60
    Soul
    -0.60
    POSITIVE LOGITS
     HasFactory
    0.69
     typelib
    0.68
    MigrationBuilder
    0.63
    ArgumentParser
    0.58
    ScopeManager
    0.57
    Datuak
    0.57
    andExpect
    0.57
     OFDb
    0.57
    ATURA
    0.57
    nage
    0.57
    Activations Density 1.973%

    No Known Activations