© 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
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 29803
    Prev
    Next
    INDEX
    Explanations

    the action of directing responsibility toward a subject.

    oai_token-act-pair · gemini-2.0-flash
    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
    deque
    -0.64
    tencent
    -0.61
    DataMember
    -0.57
     Kessler
    -0.57
    overview
    -0.57
    ตรี
    -0.56
    multer
    -0.54
    jsii
    -0.54
    sap
    -0.53
     buah
    -0.53
    POSITIVE LOGITS
     blame
    1.41
     Blame
    1.39
    Blame
    1.39
     blaming
    1.37
    blame
    1.33
     blamed
    1.29
     blames
    1.25
    脚注の使い方
    0.82
     scape
    0.81
    RenderAtEndOf
    0.77
    Activations Density 0.008%

    No Known Activations