© 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. 1918
    Prev
    Next
    INDEX
    Explanations

    under

    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
    DoubleQuotes
    -0.68
    IntoConstraints
    -0.63
     faſt
    -0.60
    ResponseWriter
    -0.59
    Tikang
    -0.59
    istoitu
    -0.57
    LayoutConstraint
    -0.56
    itans
    -0.56
    PerformLayout
    -0.55
    ="@+
    -0.55
    POSITIVE LOGITS
     clínicos
    0.49
     asli
    0.47
     repuesto
    0.47
     møte
    0.46
    tinyos
    0.46
     invokingState
    0.46
    ionario
    0.45
    apati
    0.45
     cuivre
    0.44
     producir
    0.44
    Activations Density 0.040%

    No Known Activations