© 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. 15496
    Prev
    Next
    INDEX
    Explanations

    tuples of numeric values or symbols often associated with mathematical or scientific expressions

    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
     ModelExpression
    -0.68
    "),
    -0.60
    windowFixed
    -0.59
     gainera
    -0.59
    }{||
    -0.53
    '},
    -0.53
    ItemBackground
    -0.53
    ActionMode
    -0.53
    rizona
    -0.52
    timewa
    -0.52
    POSITIVE LOGITS
    moiselle
    0.66
    httphttps
    0.57
    NewUrlParser
    0.50
    isabeth
    0.49
    greenrobot
    0.49
    rungsseite
    0.49
    líben
    0.49
     المعيارى
    0.49
    empl
    0.48
    řevě
    0.48
    Activations Density 0.065%

    No Known Activations