© 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. 1-CLT-HP
    7. 529
    Prev
    Next
    INDEX
    Explanations

    jobs

    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
     ModelExpression
    -0.74
     تضيفلها
    -0.68
     mapStateToProps
    -0.63
     esternos
    -0.58
     Normdatei
    -0.57
     nakalista
    -0.57
    }")]
    -0.56
    INTENANCE
    -0.56
    XmlAccessType
    -0.56
    OGND
    -0.54
    POSITIVE LOGITS
    minecraft
    0.54
     kasarigan
    0.48
     بيها
    0.48
     Education
    0.42
     VES
    0.42
    SIC
    0.42
    ICT
    0.41
    Ves
    0.41
     SIC
    0.41
     segno
    0.41
    Activations Density 0.047%

    No Known Activations