© 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. 4-CLT-HP
    7. 4969
    Prev
    Next
    INDEX
    Explanations

    URLs and code references

    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
    StoryboardSegue
    -0.80
    OGND
    -0.76
     NUKAT
    -0.63
    GEBURTS
    -0.62
    Hauptartikel
    -0.62
     Wordle
    -0.61
    niająca
    -0.59
    autoconfigure
    -0.58
    ])):
    -0.57
    parsedMessage
    -0.56
    POSITIVE LOGITS
    DropTable
    0.52
     
    0.44
    Seni
    0.44
     acondicionado
    0.44
     cammino
    0.43
    ost
    0.43
    Curious
    0.43
    .
    0.43
    count
    0.43
     would
    0.42
    Activations Density 0.004%

    No Known Activations