© 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. 5-CLT-HP
    7. 2015
    Prev
    Next
    INDEX
    Explanations

    Numbers and abbreviations

    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
     betweenstory
    -0.46
    InSection
    -0.44
     FetchType
    -0.42
    udt
    -0.40
     snippetHide
    -0.40
     通販
    -0.40
     eben
    -0.36
    ConstraintMaker
    -0.35
    timewa
    -0.35
     ready
    -0.34
    POSITIVE LOGITS
    osaurs
    0.69
     Castles
    0.66
    skis
    0.65
    AKES
    0.65
    DoubleQuotes
    0.65
     Armies
    0.63
    ISTAS
    0.63
    itars
    0.63
    olars
    0.62
     Clerks
    0.61
    Activations Density 0.024%

    No Known Activations