© 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. 3545
    Prev
    Next
    INDEX
    Explanations

    instructions and processes related to machine operations and programming logic

    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
    endregion
    -0.49
    긴
    -0.48
    demik
    -0.46
     discussione
    -0.46
    limin
    -0.45
     ThemeData
    -0.45
    허
    -0.45
     JpaRepository
    -0.45
     referenties
    -0.44
    mixin
    -0.43
    POSITIVE LOGITS
    Sucesor
    0.67
     fresher
    0.63
     recommen
    0.62
    typeorm
    0.61
    ensement
    0.58
    EDEFAULT
    0.58
    +#+
    0.57
    +#+#
    0.57
     betweenstory
    0.56
     reinvest
    0.56
    Activations Density 0.480%

    No Known Activations