© 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. 45506
    Prev
    Next
    INDEX
    Explanations

    FA

    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
    ur
    -0.84
    off
    -0.74
    ura
    -0.66
    gal
    -0.63
    pur
    -0.63
    ure
    -0.62
    ette
    -0.62
    UR
    -0.59
    ng
    -0.58
    rose
    -0.53
    POSITIVE LOGITS
     незавершена
    0.75
     виправивши
    0.75
    SourceChecksum
    0.74
     NavController
    0.73
    )];
    0.72
    Erreferentziak
    0.71
    WebVitals
    0.71
    ]})
    0.71
    ]]=
    0.70
    TypedDataSet
    0.69
    Activations Density 0.780%

    No Known Activations