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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31065
    Prev
    Next
    INDEX
    Explanations

    line breaks or spacing in legal documents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
    ╭
    -0.50
    IsMutable
    -0.49
    EndInit
    -0.49
     remol
    -0.48
     eing
    -0.45
     protoimpl
    -0.43
     estre
    -0.42
    onViewCreated
    -0.41
    gonic
    -0.41
    PerformLayout
    -0.41
    POSITIVE LOGITS
     Monfieur
    0.77
    Personendaten
    0.75
     Efq
    0.75
    CloseOperation
    0.74
     PopupWindow
    0.73
    intios
    0.72
     satisfait
    0.69
     rire
    0.69
    ^(@)
    0.69
    MENAFN
    0.68
    Activations Density 0.014%

    No Known Activations