© 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. 12128
    Prev
    Next
    INDEX
    Explanations

    refrigeration

    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
    expandindo
    -0.63
     <>",
    -0.62
     OFDb
    -0.59
     beginnetje
    -0.57
    InSection
    -0.55
    fillType
    -0.54
    encodeWith
    -0.52
    Portale
    -0.52
    ształ
    -0.50
    Anhalt
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.62
    BufferException
    0.57
     Racine
    0.56
    Посилання
    0.52
     Dionys
    0.50
    下载附件
    0.50
     phosphoric
    0.49
    SequentialGroup
    0.49
     contigo
    0.47
     оригіналу
    0.47
    Activations Density 0.027%

    No Known Activations