© 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. 31103
    Prev
    Next
    INDEX
    Explanations

    scenarios that involve containment or storage structures

    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
     Su
    -0.47
     presenti
    -0.47
    νη
    -0.43
     su
    -0.43
     Cameron
    -0.42
    зде
    -0.42
     Cam
    -0.42
    ंट
    -0.42
     dik
    -0.41
     than
    -0.41
    POSITIVE LOGITS
    SourceChecksum
    0.88
    abestanden
    0.87
    脚注の使い方
    0.85
    protoimpl
    0.84
    +#+#
    0.84
    OrNil
    0.84
    setVerticalGroup
    0.82
     EnglishChoose
    0.78
    SharedCtor
    0.77
    ⓧ
    0.77
    Activations Density 0.309%

    No Known Activations