© 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. 12-RES-MATRYOSHKA-DC
    7. 21587
    Prev
    Next
    INDEX
    Explanations

    terms related to directional flow and channel mechanisms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.63
    VisualStudio
    -0.58
    principalTable
    -0.58
     allAfrica
    -0.58
    XmlAccessorType
    -0.57
    iomanip
    -0.56
    rungsseite
    -0.55
    DockStyle
    -0.55
     voegen
    -0.54
    providedIn
    -0.54
    POSITIVE LOGITS
    irectional
    0.92
     bidirectional
    0.90
     Reverso
    0.83
     unid
    0.69
    RenderAtEndOf
    0.68
     arrows
    0.67
    ViewFeatures
    0.63
    jalá
    0.59
    directional
    0.58
    bid
    0.57
    Activations Density 0.035%

    No Known Activations