© 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. 12047
    Prev
    Next
    INDEX
    Explanations

    goats

    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
    RefNanny
    -0.65
     altitude
    -0.64
    riedenheit
    -0.60
     تضيفلها
    -0.60
    ,:);
    -0.59
    altitude
    -0.59
    ]='\
    -0.58
     getVersion
    -0.57
     farm
    -0.57
    mein
    -0.57
    POSITIVE LOGITS
     pinulongan
    0.55
    parsedMessage
    0.52
     begründet
    0.50
     personnalisées
    0.50
    bruik
    0.49
     roulant
    0.49
     weißt
    0.48
     NSCoder
    0.48
     and
    0.47
    LookAnd
    0.45
    Activations Density 0.016%

    No Known Activations