© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38404
    Prev
    Next
    INDEX
    Explanations

    Model

    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
    Model
    -1.01
    model
    -0.75
    NO
    -0.68
     avancée
    -0.65
    models
    -0.63
     chaude
    -0.63
     seksual
    -0.63
     sherds
    -0.63
     oes
    -0.61
     pulito
    -0.61
    POSITIVE LOGITS
    Czytaj
    0.73
    ništvo
    0.72
    )))));
    0.68
    ']))
    
    0.68
    findpost
    0.68
    ftant
    0.67
    "")
    0.66
    )』
    0.66
    OLIS
    0.65
    "])
    
    0.65
    Activations Density 0.046%

    No Known Activations