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. 16342
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to difficulty and adversity

    oai_token-act-pair · gemini-2.0-flash

    struggle

    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
    RectangleBorder
    -0.93
    RenderAtEndOf
    -0.91
    ]";
    -0.89
    %";
    -0.87
     ſta
    -0.84
     propOrder
    -0.83
    ]');
    -0.80
     ſind
    -0.80
     tartalomajánló
    -0.80
     Normdatei
    -0.78
    POSITIVE LOGITS
    .
    0.44
     to
    0.40
     disposição
    0.40
     by
    0.40
    by
    0.39
     segno
    0.38
    ban
    0.38
    Ancien
    0.37
    Vincent
    0.36
     Vincent
    0.36
    Activations Density 1.275%

    No Known Activations