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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14960
    Prev
    Next
    INDEX
    Explanations

    invariants and properties related to mathematical structures, particularly root systems and their classifications

    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
    gameserver
    -0.70
    abetta
    -0.68
    kháu
    -0.68
    bouncycastle
    -0.63
    rrggbb
    -0.56
     Италијани
    -0.56
    TagHelper
    -0.56
    makeConstraints
    -0.54
    ❉
    -0.52
     saling
    -0.52
    POSITIVE LOGITS
    potent
    1.05
     Vib
    0.99
    valently
    0.92
    omp
    0.88
    mouseout
    0.84
     rains
    0.83
    accordion
    0.82
    Vib
    0.73
    OMP
    0.68
    </tfoot>
    0.62
    Activations Density 0.010%

    No Known Activations