© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32173
    Prev
    Next
    INDEX
    Explanations

    expressions indicating mathematical mappings or transformations

    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
    jednoc
    -0.63
     tearDown
    -0.55
     Και
    -0.54
     respondent
    -0.53
     riktig
    -0.53
    Espèce
    -0.52
     (!__
    -0.52
    xAxis
    -0.52
     politiet
    -0.52
    ัง
    -0.51
    POSITIVE LOGITS
    mapsto
    1.51
    ↦
    1.19
    webElementXpaths
    0.86
     мәкал
    0.79
    ItemBackground
    0.69
    (&:
    0.66
     Jä
    0.65
    اديم
    0.64
    lassification
    0.63
    astify
    0.63
    Activations Density 0.001%

    No Known Activations