© 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. 365
    Prev
    Next
    INDEX
    Explanations

    technical processes

    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
     graphite
    -1.47
     Graphite
    -1.29
    Grap
    -0.99
     graphi
    -0.91
    grap
    -0.88
     Efq
    -0.85
    ValueGeneration
    -0.79
     Walkover
    -0.73
    yntaxException
    -0.73
     protoimpl
    -0.72
    POSITIVE LOGITS
     propias
    0.47
    pred
    0.44
     consecuencias
    0.44
    Prior
    0.42
    moires
    0.41
     comb
    0.41
    Pred
    0.40
     form
    0.40
    localPosition
    0.40
     dyr
    0.40
    Activations Density 0.006%

    No Known Activations