© 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. 12437
    Prev
    Next
    INDEX
    Explanations

    references to redundancy or redundant features

    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
    SharedCtor
    -0.56
    yield
    -0.55
     estimés
    -0.53
     initComponents
    -0.52
    frog
    -0.50
    stateProvider
    -0.50
     Sco
    -0.47
    LookAnd
    -0.47
    Chapitre
    -0.47
    Література
    -0.47
    POSITIVE LOGITS
     redundancy
    3.28
     redundant
    3.22
    redund
    3.05
     Redund
    3.03
     redund
    2.84
    Redund
    2.66
    冗
    1.42
     superfluous
    1.13
     superflu
    0.87
     surplus
    0.84
    Activations Density 0.003%

    No Known Activations