© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15313
    Prev
    Next
    INDEX
    Explanations

    references to legal allegations or claims involving negligence or arising from negligent conduct

    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
    Palmar
    -0.76
    adpleegd
    -0.70
     esternos
    -0.70
    Javadoc
    -0.69
    esgue
    -0.69
    دانشنامهٔ
    -0.68
     ligiloj
    -0.66
     snippetHide
    -0.64
    躇
    -0.63
    Clik
    -0.63
    POSITIVE LOGITS
     arising
    1.85
     ARISING
    0.96
     stemming
    0.77
    ınt
    0.49
    ógicas
    0.46
     shall
    0.45
     округ
    0.45
    EndContext
    0.45
    الحياه
    0.45
    ystis
    0.44
    Activations Density 0.002%

    No Known Activations