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. 44953
    Prev
    Next
    INDEX
    Explanations

    prevalence presence

    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
     presence
    -1.89
    presence
    -1.73
     Presence
    -1.55
     présence
    -1.52
    present
    -1.41
     present
    -1.39
     presencia
    -1.39
    Presence
    -1.38
     présentes
    -1.34
     présent
    -1.31
    POSITIVE LOGITS
     of
    0.98
     from
    0.68
     in
    0.67
     with
    0.60
    ,
    0.59
    ment
    0.57
     between
    0.54
     and
    0.52
     at
    0.50
     is
    0.50
    Activations Density 0.089%

    No Known Activations