© 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. 76586
    Prev
    Next
    INDEX
    Explanations

    across

    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
     <=",
    -0.70
    Carriera
    -0.66
     فريبيس
    -0.66
     المعيارى
    -0.65
    SizeF
    -0.63
    ftagPool
    -0.62
     Commencez
    -0.60
    NOPQRST
    -0.59
    WebVitals
    -0.59
     Delivery
    -0.59
    POSITIVE LOGITS
    LikeLiked
    0.55
     category
    0.51
    ?></
    0.51
     e
    0.46
    Explicación
    0.44
    NewRow
    0.43
     dring
    0.43
     channel
    0.40
     CP
    0.40
     spend
    0.39
    Activations Density 0.001%

    No Known Activations