© 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. 93545
    Prev
    Next
    INDEX
    Explanations

    cripts

    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
    rane
    -0.96
    cripts
    -0.85
     BoxFit
    -0.70
    rased
    -0.68
    SBATCH
    -0.58
    JNIEnv
    -0.58
    ⓧ
    -0.58
    djangoproject
    -0.58
    tagext
    -0.55
    ranes
    -0.54
    POSITIVE LOGITS
    paravant
    0.58
     Arrangement
    0.56
     spoons
    0.56
     Capit
    0.55
     Orch
    0.54
    usercontent
    0.54
     ſhe
    0.53
    endfor
    0.53
     Juf
    0.53
     stools
    0.52
    Activations Density 0.199%

    No Known Activations