© 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. 5628
    Prev
    Next
    INDEX
    Explanations

    ingredients and quantities in recipes

    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
    tagHelperRunner
    -0.57
    borderSide
    -0.56
    WebVitals
    -0.53
     flavored
    -0.52
    ();)
    -0.51
     edição
    -0.51
     Shakspeare
    -0.51
     themselves
    -0.49
     delicious
    -0.49
     flavor
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.75
    RegressionTest
    0.69
     ISNI
    0.63
     ModelExpression
    0.63
    GEBURTSDATUM
    0.63
     Logement
    0.58
    pexpr
    0.58
    RetentionPolicy
    0.57
    melis
    0.57
    titleMargin
    0.56
    Activations Density 0.041%

    No Known Activations