© 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. 4-CLT-HP
    7. 1127
    Prev
    Next
    INDEX
    Explanations

    punctuation/contractions

    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
    RenderAtEndOf
    -0.60
     Drapeau
    -0.60
     SwitchCompat
    -0.55
     Diſ
    -0.53
    ụn
    -0.52
     خارجية
    -0.50
    WireFormatLite
    -0.49
     ettei
    -0.49
     IHC
    -0.49
     Majefty
    -0.47
    POSITIVE LOGITS
     necessarily
    1.05
     have
    0.75
     be
    0.74
     get
    0.74
     bother
    0.73
     ModelExpression
    0.70
     satisfy
    0.69
     budge
    0.69
     seem
    0.69
     take
    0.69
    Activations Density 0.041%

    No Known Activations