© 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. 1-CLT-HP
    4. 13121
    Prev
    Next
    INDEX
    Explanations

    subscription

    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
     powder
    -1.28
     Powder
    -1.19
    powder
    -1.06
    Powder
    -1.00
     powders
    -0.93
     powdered
    -0.79
     POW
    -0.74
     bubuk
    -0.64
    Pow
    -0.63
     Pow
    -0.63
    POSITIVE LOGITS
    hall
    0.48
     rhestr
    0.47
     发表于
    0.47
    žius
    0.47
    ing
    0.47
     INTERESAR
    0.46
     yyr
    0.45
     MainAxisSize
    0.45
     mattina
    0.45
    +:+
    0.45
    Activations Density 0.007%

    No Known Activations