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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2280
    Prev
    Next
    INDEX
    Explanations

    references to youth and generational conflict surrounding art and entertainment.

    oai_token-act-pair · gemini-2.0-flash

    party

    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
     سكانية
    -0.84
     initComponents
    -0.73
     дописавши
    -0.67
     mergeFrom
    -0.66
    />";
    -0.64
     ControllerBase
    -0.62
     мәкал
    -0.60
    المناصب
    -0.59
    EndInit
    -0.59
    ResumeLayout
    -0.58
    POSITIVE LOGITS
     parties
    0.56
     party
    0.56
    parties
    0.54
     Dolly
    0.53
    party
    0.53
     PARTIES
    0.53
     acide
    0.50
     base
    0.47
    曖昧さ回避
    0.46
     acides
    0.46
    Activations Density 6.356%

    No Known Activations