© 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. 0-CLT-HP
    7. 39917
    Prev
    Next
    INDEX
    Explanations

    hinges

    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
     motivation
    -0.75
    GOTREF
    -0.69
     flexibility
    -0.67
    e
    -0.58
    })*/
    -0.56
     motivated
    -0.56
    EEEE
    -0.55
    %)$
    -0.55
     motivations
    -0.54
    yid
    -0.54
    POSITIVE LOGITS
    ally
    0.77
    ized
    0.63
    Lähteet
    0.63
     Roskov
    0.63
    ian
    0.55
    setupUi
    0.54
    izing
    0.54
    queryInterface
    0.54
    ists
    0.52
     <=",
    0.51
    Activations Density 0.089%

    No Known Activations