© 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. 96170
    Prev
    Next
    INDEX
    Explanations

    First-person pronouns

    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
    ParallelGroup
    -0.54
     跳转至
    -0.51
     consultato
    -0.50
    ?";
    -0.49
     veux
    -0.48
    vedať
    -0.47
     miliardi
    -0.47
    ConstraintMaker
    -0.45
    WireFormatLite
    -0.45
    AccessorTable
    -0.45
    POSITIVE LOGITS
    HtmlAttribute
    0.61
    EOUT
    0.56
     препратки
    0.54
    entran
    0.53
     nahilalakip
    0.52
    GEBURTSDATUM
    0.52
    انيف
    0.52
    XmlAccessType
    0.49
    GEBURTS
    0.48
    épendance
    0.48
    Activations Density 0.000%

    No Known Activations