© 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. 95244
    Prev
    Next
    INDEX
    Explanations

    Adding detail and clarification

    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
    </h6>
    -0.61
    **/
    -0.57
    </h5>
    -0.57
    });*/
    -0.55
    *************/
    -0.54
    ************/
    -0.54
    </h2>
    -0.51
    Moreover
    -0.50
     plus
    -0.50
     Moreover
    -0.50
    POSITIVE LOGITS
    WebElementEntity
    0.69
     it
    0.69
    esModule
    0.67
    WithMany
    0.65
    setVerticalGroup
    0.63
    findpost
    0.63
    ByVersion
    0.62
     they
    0.57
     we
    0.56
    UnusedPrivate
    0.54
    Activations Density 0.002%

    No Known Activations