© 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. 5-CLT-HP
    7. 553
    Prev
    Next
    INDEX
    Explanations

    Contact information requests

    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
    findpost
    -0.55
     estekak
    -0.50
     nocturno
    -0.48
     ogóle
    -0.48
    ertale
    -0.46
    hlander
    -0.42
     nocturna
    -0.41
    esModule
    -0.41
    WebElementEntity
    -0.41
    ècie
    -0.40
    POSITIVE LOGITS
     a
    0.91
     your
    0.81
    GEBURTSDATUM
    0.68
     an
    0.66
     the
    0.65
    WebpackPlugin
    0.64
    fromnode
    0.61
     someone
    0.58
    parsedMessage
    0.58
     free
    0.58
    Activations Density 0.000%

    No Known Activations