© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77141
    Prev
    Next
    INDEX
    Explanations

    Formal writing contexts

    np_max-act-logits · 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
    yntaxException
    -0.76
     '\\;'
    -0.70
    BeginContext
    -0.69
    UnusedPrivate
    -0.64
    mybatisplus
    -0.63
     onResponse
    -0.63
     виправивши
    -0.63
    Personensuche
    -0.61
     OMITBAD
    -0.59
    ymce
    -0.59
    POSITIVE LOGITS
     [*]
    0.47
    tiskt
    0.47
    itis
    0.47
     −
    0.45
    ANZA
    0.44
    ocardio
    0.44
     väg
    0.43
     colgantes
    0.43
     culturelles
    0.42
    arkhand
    0.40
    Activations Density 0.000%

    No Known Activations