© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13963
    Prev
    Next
    INDEX
    Explanations

    references to specific numbered citations or case references

    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
    pos
    -0.61
    cs
    -0.60
    3
    -0.60
    "
    -0.57
    ly
    -0.57
    est
    -0.57
    ว์
    -0.56
    iste
    -0.55
    der
    -0.54
    iso
    -0.54
    POSITIVE LOGITS
    ientôt
    0.99
     myſelf
    0.92
    =$?
    0.90
    ."));
    0.86
    $")
    0.86
     feroit
    0.85
    %)$
    0.84
    '):
    
    0.84
     nôtre
    0.84
    "):
    
    0.84
    Activations Density 0.060%

    No Known Activations