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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2299
    Prev
    Next
    INDEX
    Explanations

    words related to different types of food in an ethnic restaurant review

    oai_token-act-pair · gemini-2.0-flash

    Food related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    تقاوى
    -0.81
    Jeografia
    -0.75
    Tikang
    -0.73
    Personendaten
    -0.68
    IVEREF
    -0.66
    expandindo
    -0.65
    TestBed
    -0.65
     drinks
    -0.65
     transfieras
    -0.64
    PerformLayout
    -0.63
    POSITIVE LOGITS
     bun
    0.52
     EventArgs
    0.51
    lland
    0.48
    ulare
    0.47
     dum
    0.44
    Hinweise
    0.44
    تام
    0.44
    DialogInterface
    0.43
     становника
    0.43
    AttributeName
    0.43
    Activations Density 6.021%

    No Known Activations