© 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. 15293
    Prev
    Next
    INDEX
    Explanations

    references to a specific point or location

    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
    runApp
    -0.63
    gitto
    -0.58
    fxml
    -0.54
    addContainerGap
    -0.53
     TPE
    -0.52
    StreetMap
    -0.52
    jsdelivr
    -0.52
     plaît
    -0.51
     WPF
    -0.51
     MotionEvent
    -0.50
    POSITIVE LOGITS
     pointed
    0.73
     pointing
    0.68
     point
    0.68
     purpoſe
    0.64
    ----</
    0.60
     previous
    0.59
    Corollary
    0.59
    StructEnd
    0.59
     Roskov
    0.59
     leveled
    0.57
    Activations Density 0.016%

    No Known Activations