© 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. 91767
    Prev
    Next
    INDEX
    Explanations

    when

    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
    awtextra
    -0.77
    UserScript
    -0.77
    ]")]
    -0.75
    providedIn
    -0.73
    StoryboardSegue
    -0.71
     '/':
    -0.69
    AccessorTable
    -0.66
    EClass
    -0.65
    DBNull
    -0.65
     فريبيس
    -0.64
    POSITIVE LOGITS
    <bos>
    1.00
     blanches
    0.55
     itself
    0.53
     itſelf
    0.52
     writes
    0.51
     resté
    0.51
     becomes
    0.50
     сама
    0.50
     knows
    0.50
     does
    0.50
    Activations Density 0.023%

    No Known Activations