© 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. 76585
    Prev
    Next
    INDEX
    Explanations

    7

    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
     Sosten
    -0.52
    InjectAttribute
    -0.51
     '{@
    -0.48
     Gas
    -0.46
    nocache
    -0.46
    Dichloropropene
    -0.46
    rxjs
    -0.45
    ఔ
    -0.44
    >[]
    -0.44
     zan
    -0.44
    POSITIVE LOGITS
    AsUp
    0.59
     étoient
    0.55
     avoient
    0.54
    seamnă
    0.52
    dify
    0.52
     getLast
    0.52
     quitte
    0.49
     personnalité
    0.49
    dam
    0.48
     giudizio
    0.48
    Activations Density 0.001%

    No Known Activations