© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    Ranges

    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
     Efq
    -0.93
     Theſe
    -0.89
    busch
    -0.80
    HICLE
    -0.79
    anus
    -0.79
     myſelf
    -0.79
    Chham
    -0.78
    sterious
    -0.78
    itative
    -0.77
     sèche
    -0.77
    POSITIVE LOGITS
    \{\\
    0.62
    con
    0.61
    i
    0.60
    __":
    0.59
    .
    0.55
    -
    0.55
    ek
    0.54
    writeFieldEnd
    0.54
    epar
    0.54
    are
    0.54
    Activations Density 1.173%

    No Known Activations