© 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. 5901
    Prev
    Next
    INDEX
    Explanations

    conversation fragments

    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
    InstanceState
    -0.78
     lenker
    -0.68
    __(/*!
    -0.68
     ſtate
    -0.68
     تضيفلها
    -0.65
     preſent
    -0.63
    सन्दर्भ
    -0.63
    kloped
    -0.61
    bootstrapcdn
    -0.61
     ſeveral
    -0.61
    POSITIVE LOGITS
    MigrationBuilder
    0.54
     and
    0.50
     Efficacy
    0.47
    https
    0.44
    TAWA
    0.44
     hábitos
    0.43
    وزيع
    0.43
     TOWNS
    0.43
    及其
    0.43
    atalog
    0.42
    Activations Density 0.006%

    No Known Activations