© 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. 8824
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to hardware and programming

    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
    blockList
    -1.51
    ết
    -0.58
    DICTION
    -0.57
     Pohl
    -0.56
    ท้าย
    -0.55
     Lindberg
    -0.55
    andExpect
    -0.54
    bonucle
    -0.53
    Dichlorobenzene
    -0.53
     picioare
    -0.53
    POSITIVE LOGITS
    Blockly
    2.89
     Blockly
    2.23
     تانيه
    0.69
    $_['
    0.58
     Roskov
    0.58
    MigrationBuilder
    0.57
    SqlSession
    0.56
     lenker
    0.56
     Administrativna
    0.55
    horizontalLayout
    0.55
    Activations Density 0.044%

    No Known Activations