© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40658
    Prev
    Next
    INDEX
    Explanations

    full

    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
     sites
    -0.63
     content
    -0.62
     stories
    -0.60
     reaſon
    -0.60
     cabins
    -0.59
     ſame
    -0.59
     seats
    -0.58
     sets
    -0.57
     servers
    -0.56
     shuts
    -0.56
    POSITIVE LOGITS
    ftagPool
    0.69
     تانيه
    0.63
    ResumeLayout
    0.60
    AxisAlignment
    0.57
    Espèce
    0.57
    exitRule
    0.53
    ANTLR
    0.52
    Portail
    0.48
    continence
    0.48
     SqlDbType
    0.47
    Activations Density 0.094%

    No Known Activations