© 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. 96044
    Prev
    Next
    INDEX
    Explanations

    to

    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
     bär
    -0.57
     precisione
    -0.57
     autunno
    -0.56
     typelib
    -0.55
    Few
    -0.54
     coraggio
    -0.53
     capables
    -0.53
     artificiales
    -0.51
     colpa
    -0.51
     calitate
    -0.50
    POSITIVE LOGITS
    ArgsConstructor
    0.64
    esModule
    0.62
     popular
    0.56
     '{@
    0.56
     initial
    0.54
    ATRO
    0.54
    ochim
    0.53
     expectation
    0.53
     lenker
    0.53
    ÍO
    0.52
    Activations Density 0.001%

    No Known Activations