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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12409
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical quantities or counts

    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
    fuck
    -0.78
    ()?;
    -0.72
     ſhall
    -0.68
     twenty
    -0.67
     femmin
    -0.67
     shewn
    -0.66
     fuck
    -0.66
     Fuck
    -0.65
     tdci
    -0.63
     compét
    -0.63
    POSITIVE LOGITS
     Forty
    1.61
     Sixty
    1.60
     Thirty
    1.50
     Fifty
    1.49
    Fifty
    1.47
    Forty
    1.47
     Eighty
    1.47
     Seventy
    1.41
     Twenty
    1.40
    Sixty
    1.39
    Activations Density 0.005%

    No Known Activations