© 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. 42393
    Prev
    Next
    INDEX
    Explanations

    state

    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
    ReusableCell
    -0.61
    RepeatedField
    -0.53
    rum
    -0.47
    Portály
    -0.46
    SPECIFIED
    -0.46
    rado
    -0.46
    URED
    -0.46
    mc
    -0.45
    aker
    -0.45
    rd
    -0.45
    POSITIVE LOGITS
    <bos>
    0.78
     raiſ
    0.63
     itſelf
    0.59
     Plan
    0.59
     Drapeau
    0.54
     Affairs
    0.53
     Deal
    0.53
    chiha
    0.53
     Setup
    0.52
     themſelves
    0.52
    Activations Density 1.686%

    No Known Activations