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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1558
    Prev
    Next
    INDEX
    Explanations

    various words associated with families, relationships, and events in their lives.

    oai_token-act-pair · gemini-2.0-flash

    Negative situations

    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
     are
    -0.63
    DockStyle
    -0.59
     after
    -0.57
    PyExc
    -0.57
     have
    -0.57
    spesies
    -0.56
     After
    -0.56
     Because
    -0.53
    utilisons
    -0.51
    After
    -0.51
    POSITIVE LOGITS
    تقاوى
    0.64
    {}",
    0.62
    ]}"
    0.57
    ')")
    0.57
    }{*}{
    0.57
    .";
    
    0.57
    }";
    0.56
     CURIAM
    0.56
    elry
    0.55
    seteq
    0.53
    Activations Density 32.970%

    No Known Activations