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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14630
    Prev
    Next
    INDEX
    Explanations

    references to emission or release of particles or energy

    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
    VersionUID
    -0.71
    曖昧さ回避
    -0.58
     pulumi
    -0.58
    BeginContext
    -0.57
    nasel
    -0.53
    styrelsen
    -0.52
    bollah
    -0.52
    льности
    -0.52
    kunta
    -0.51
    ajevo
    -0.51
    POSITIVE LOGITS
     Guards
    1.60
     guards
    1.53
     emitted
    1.46
    Guards
    1.19
    guards
    0.84
     ejected
    0.80
     radiated
    0.70
     TextAppearance
    0.69
    StructEnd
    0.69
    دانشنامهٔ
    0.67
    Activations Density 0.002%

    No Known Activations