Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16220
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.74
    ьаж
    -0.73
    createCanvas
    -0.70
    ResumeLayout
    -0.67
    RegressionTest
    -0.63
    CppMethod
    -0.63
    లాలు
    -0.63
     NSCoder
    -0.61
     كومونز
    -0.60
    IndentedString
    -0.60
    POSITIVE LOGITS
    principalColumn
    0.54
    }")]
    0.50
    "}"
    0.48
    Бахар
    0.47
     arrayOf
    0.46
     }^{\
    0.45
     gốc
    0.44
    NameInMap
    0.44
    anover
    0.43
     tune
    0.42
    Activations Density 1.281%

    No Known Activations