© 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. 1-CLT-HP
    7. 10073
    Prev
    Next
    INDEX
    Explanations

    orphans

    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
    icium
    -0.71
     Haywood
    -0.56
    beek
    -0.55
    INK
    -0.48
     ketahui
    -0.47
    EX
    -0.46
     peuples
    -0.44
    vington
    -0.44
    IC
    -0.44
     Single
    -0.44
    POSITIVE LOGITS
     >=",
    0.76
     onOptions
    0.68
     للمعارف
    0.67
    ########.
    0.66
    tanleria
    0.66
     GridLayout
    0.65
    PhysRev
    0.63
     numberWith
    0.62
     GreatSchools
    0.62
    المشاركات
    0.61
    Activations Density 0.013%

    No Known Activations