© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44142
    Prev
    Next
    INDEX
    Explanations

    temperature/heating

    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
     heats
    -0.84
     themſelves
    -0.63
     pleaſure
    -0.62
     cauſe
    -0.59
     habet
    -0.59
     deſt
    -0.57
    tags
    -0.54
     deliver
    -0.53
     houſe
    -0.53
     dries
    -0.52
    POSITIVE LOGITS
    AutoresizingMask
    0.68
     EconPapers
    0.64
     CreateTagHelper
    0.63
    GTCX
    0.62
    ValueStyle
    0.60
    FontOfSize
    0.60
     ويكيپيديا
    0.60
     autorytatywna
    0.59
    FunctionFlags
    0.58
     accede
    0.58
    Activations Density 0.148%

    No Known Activations