© 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. 92601
    Prev
    Next
    INDEX
    Explanations

    Computer code and errors

    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
    MigrationBuilder
    -0.74
    RenderAtEndOf
    -0.48
    ukone
    -0.48
     françaises
    -0.47
    maybe
    -0.46
     оригіналу
    -0.45
     perhaps
    -0.45
     maybe
    -0.44
     megfe
    -0.44
    wikk
    -0.44
    POSITIVE LOGITS
     saites
    0.65
    EndProject
    0.57
    UnusedPrivate
    0.56
    DebuggerNonUser
    0.55
    KeyId
    0.53
     iload
    0.53
    ыгана
    0.52
    zaine
    0.52
    fordable
    0.52
    mybatisplus
    0.52
    Activations Density 0.017%

    No Known Activations