© 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. 1-CLT-HP
    7. 46051
    Prev
    Next
    INDEX
    Explanations

    time

    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
    InjectAttribute
    -0.93
     resourceCulture
    -0.90
    SourceChecksum
    -0.84
    TargetException
    -0.74
    новништво
    -0.74
    Jereo
    -0.71
    ]")]
    -0.71
     متعلقه
    -0.70
     Signalez
    -0.69
    principalTable
    -0.68
    POSITIVE LOGITS
    ntö
    0.49
     specifically
    0.45
    şık
    0.43
     authority
    0.42
     quí
    0.41
    gina
    0.40
     tric
    0.39
    UMB
    0.39
     engravings
    0.39
     testigo
    0.39
    Activations Density 0.003%

    No Known Activations