© 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. 5-CLT-HP
    7. 97110
    Prev
    Next
    INDEX
    Explanations

    cabin

    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
     went
    -0.49
     interacted
    -0.46
    '
    -0.44
     had
    -0.43
     knew
    -0.42
     existed
    -0.42
     were
    -0.42
     habían
    -0.41
     depended
    -0.40
     showed
    -0.40
    POSITIVE LOGITS
    LookAnd
    0.79
    oflavin
    0.78
     فريبيس
    0.78
    GEBURTSDATUM
    0.76
     '\\;'
    0.76
     lenker
    0.73
     kaynağından
    0.73
    ConstraintMaker
    0.72
    windowFixed
    0.72
    Portale
    0.71
    Activations Density 0.000%

    No Known Activations