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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10168
    Prev
    Next
    INDEX
    Explanations

    statements referring to enhancing or fixing something

    oai_token-act-pair · gemini-2.0-flash

    improving things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/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
    principalTable
    -0.73
    webElement
    -0.71
    GEBURTS
    -0.71
     препратки
    -0.69
    DeleteBehavior
    -0.68
     TextAlign
    -0.68
     nonUne
    -0.66
    InputBorder
    -0.65
    IVEREF
    -0.65
     виправивши
    -0.63
    POSITIVE LOGITS
    enumi
    0.61
    Abp
    0.47
     matéri
    0.45
     alguma
    0.42
     his
    0.41
    הערות
    0.40
    Geral
    0.40
    everything
    0.40
     sonder
    0.40
    itself
    0.40
    Activations Density 6.319%

    No Known Activations