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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 2117
    Prev
    Next
    INDEX
    Explanations

    contractions with "not", auxiliary verbs, and modal verbs

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    U
    -0.44
    cb
    -0.43
     jam
    -0.42
     and
    -0.41
    span
    -0.40
    bibliothek
    -0.40
     kanssa
    -0.40
    um
    -0.39
    gel
    -0.39
     stør
    -0.38
    POSITIVE LOGITS
    PerformLayout
    0.93
     Процитовано
    0.79
     CreateTagHelper
    0.77
    ISupport
    0.77
     MainAxisSize
    0.77
     Exacts
    0.76
    `,
    
    0.76
    istoitu
    0.75
    endforeach
    0.73
    >-->
    0.73
    Activations Density 1.824%

    No Known Activations