© 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. 22926
    Prev
    Next
    INDEX
    Explanations

    questions related to seeking help or guidance

    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
     unless
    -0.48
     Unless
    -0.48
    unless
    -0.47
    blico
    -0.44
     personal
    -0.43
    acaktır
    -0.43
    ষ
    -0.42
     것입니다
    -0.42
    enuto
    -0.41
    はじめに
    -0.41
    POSITIVE LOGITS
    ConstraintMaker
    1.00
    ?
    0.95
     propOrder
    0.93
    ()?
    0.91
    ’?
    0.90
    ?”
    0.89
    StoryboardSegue
    0.88
    ?’
    0.88
     Chwiliwch
    0.87
    ?
    0.85
    Activations Density 0.047%

    No Known Activations