© 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. 12139
    Prev
    Next
    INDEX
    Explanations

    Technical applications/solutions

    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
    цездатний
    -0.50
    туга
    -0.48
     بيها
    -0.47
    Ola
    -0.47
    Tro
    -0.47
    ecar
    -0.46
    ctomy
    -0.45
    CompilerServices
    -0.44
     down
    -0.44
    carat
    -0.44
    POSITIVE LOGITS
    LookAnd
    0.76
    Przypisy
    0.72
     tartalomajánló
    0.69
    __':
    0.65
    UnusedPrivate
    0.65
     bill
    0.63
     дописавши
    0.62
    KommentareTeilen
    0.60
    __':
    0.59
    featureID
    0.59
    Activations Density 0.022%

    No Known Activations