© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43130
    Prev
    Next
    INDEX
    Explanations

    deck, alignment, warming

    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
     deck
    -1.18
    deck
    -1.12
     Deck
    -1.02
    Deck
    -0.91
     DECK
    -0.90
     Alignment
    -0.80
     alignment
    -0.78
    Alignment
    -0.73
    decks
    -0.69
    alignment
    -0.68
    POSITIVE LOGITS
    InjectAttribute
    0.77
     '\\;'
    0.75
     Normdatei
    0.74
    principalTable
    0.74
    styleType
    0.72
    XmlAccessType
    0.71
    verwijspagina
    0.71
    parsedMessage
    0.69
    .*")]
    0.66
     IndexPath
    0.66
    Activations Density 0.123%

    No Known Activations