© 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. 20-CLT-HP
    7. 77265
    Prev
    Next
    INDEX
    Explanations

    Formal documents

    np_max-act-logits · 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
    SourceChecksum
    -0.76
     GenerationType
    -0.69
    #+#
    -0.65
    processable
    -0.58
    openzeppelin
    -0.58
     cellpadding
    -0.57
    jsdelivr
    -0.56
    Читати
    -0.54
    bewerken
    -0.53
    Fordítás
    -0.52
    POSITIVE LOGITS
     embarrass
    0.57
     disabilities
    0.57
     rights
    0.55
    NgModule
    0.53
    makeText
    0.53
     views
    0.53
     Suffer
    0.52
     position
    0.51
    ViewInit
    0.51
     relations
    0.50
    Activations Density 0.000%

    No Known Activations