© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13006
    Prev
    Next
    INDEX
    Explanations

    baking, temperature, architecture

    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
     baked
    -1.77
     Baked
    -1.48
    baked
    -1.48
    Baked
    -1.26
     bake
    -1.19
    bake
    -0.97
    Bake
    -0.96
     Bake
    -0.94
     baking
    -0.60
     Baking
    -0.58
    POSITIVE LOGITS
    elemField
    0.80
     snippetHide
    0.74
     <=",
    0.69
    Personendaten
    0.67
     '\\;'
    0.65
    drawSprites
    0.61
    parsedMessage
    0.60
    μφωνα
    0.56
    GEBURTSDATUM
    0.54
    ///</
    0.53
    Activations Density 0.005%

    No Known Activations