© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    references to system signal errors and related system fault messages

    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
    ,
    -0.68
    .
    -0.65
    it
    -0.64
     &
    -0.63
     So
    -0.63
     (
    -0.62
    <eos>
    -0.61
    c
    -0.61
     I
    -0.60
     
    -0.60
    POSITIVE LOGITS
     يتيمه
    1.30
    aarrggbb
    1.16
    enterOuterAlt
    1.15
    IntoConstraints
    1.12
    SharedDtor
    1.12
    __":
    1.10
    featureID
    1.09
     itſelf
    1.09
    __":
    1.06
    __':
    1.05
    Activations Density 0.228%

    No Known Activations