© 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. 1250
    Prev
    Next
    INDEX
    Explanations

    Locations, art, and code

    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
     myſelf
    -2.47
     Monfieur
    -2.42
     Efq
    -2.31
     itſelf
    -2.27
     auffi
    -2.20
     ainfi
    -2.17
     ſtate
    -2.14
     pleaſure
    -2.14
     himſelf
    -2.13
     ſever
    -2.11
    POSITIVE LOGITS
     
    1.24
     (
    1.18
    ,
    1.14
     in
    1.10
     of
    1.09
     and
    1.09
    .
    1.07
     "
    1.04
    ↵↵
    1.00
    <eos>
    0.99
    Activations Density 0.120%

    No Known Activations