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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14233
    Prev
    Next
    INDEX
    Explanations

    references to bona fide or genuine reasons or justifications

    oai_token-act-pair · gpt-4.1-nano
    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
    laken
    -0.60
     Ling
    -0.51
    外部リンク
    -0.49
     maxim
    -0.46
    пита
    -0.45
     Дата
    -0.45
     catal
    -0.44
    資
    -0.43
    Lähteet
    -0.43
     אור
    -0.43
    POSITIVE LOGITS
     {:
    1.20
     fide
    1.12
    idu
    1.11
    SourceChecksum
    0.99
     Ottawa
    0.86
     chassis
    0.85
    WriteBarrier
    0.84
    Personendaten
    0.81
     NSCoder
    0.79
     suicidal
    0.79
    Activations Density 0.004%

    No Known Activations