© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    //

    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
    ↵
    -0.56
     See
    -0.54
     
    -0.50
     You
    -0.49
     Go
    -0.46
     Her
    -0.46
     Por
    -0.45
    루
    -0.44
     How
    -0.43
    Wash
    -0.42
    POSITIVE LOGITS
     Efq
    0.80
    verwijspagina
    0.80
    WritableDatabase
    0.78
     SwitchCompat
    0.78
     Majefty
    0.75
     صوتيه
    0.74
    BeginContext
    0.73
     createContext
    0.73
     estimés
    0.72
    DispatchToProps
    0.71
    Activations Density 0.002%

    No Known Activations