© 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. 40051
    Prev
    Next
    INDEX
    Explanations

    an

    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
     abundance
    -0.79
     asylum
    -0.73
    abundance
    -0.70
     influx
    -0.70
     all
    -0.69
     Evening
    -0.68
     amnesty
    -0.68
     <=",
    -0.67
     expert
    -0.66
     ultimatum
    -0.66
    POSITIVE LOGITS
     n
    0.63
    writeFieldEnd
    0.49
    n
    0.48
     s
    0.48
     r
    0.46
     li
    0.44
     JADX
    0.44
    écart
    0.43
     str
    0.42
     l
    0.41
    Activations Density 0.573%

    No Known Activations