Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39686
    Prev
    Next
    INDEX
    Explanations

    stages

    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
     stages
    -1.80
     phases
    -1.59
    stages
    -1.45
     cycles
    -1.44
     Stages
    -1.33
     Phases
    -1.28
    phases
    -1.24
     cycle
    -1.20
    Stages
    -1.09
    Phases
    -1.06
    POSITIVE LOGITS
    y
    0.60
    e
    0.54
    on
    0.51
    a
    0.49
     of
    0.48
    o
    0.47
     épaules
    0.45
    eron
    0.41
    de
    0.40
    onna
    0.40
    Activations Density 0.035%

    No Known Activations