© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23628
    Prev
    Next
    INDEX
    Explanations

    references to specific research studies or citations

    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
    UnsafeEnabled
    -0.47
    $\
    -0.45
    <blockquote>
    -0.45
     Dr
    -0.43
    ingan
    -0.42
    icto
    -0.41
     toJson
    -0.40
    Relacion
    -0.40
     Goldstein
    -0.39
     leg
    -0.39
    POSITIVE LOGITS
    ########.
    0.84
    تقاوى
    0.82
    providedIn
    0.81
    ValueStyle
    0.80
    AndEndTag
    0.77
     فريبيس
    0.76
     незавершена
    0.75
     transfieras
    0.73
    styleType
    0.72
    tagHelperRunner
    0.71
    Activations Density 0.004%

    No Known Activations