© 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. 2580
    Prev
    Next
    INDEX
    Explanations

    references to significant findings or results in scientific contexts

    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
    ra
    -0.53
    so
    -0.50
     дол
    -0.45
    no
    -0.44
    a
    -0.43
    as
    -0.42
    مئ
    -0.41
    Without
    -0.41
    V
    -0.41
     adultes
    -0.40
    POSITIVE LOGITS
    migrationBuilder
    1.22
     مشين
    1.03
    setVerticalGroup
    0.93
    aarrggbb
    0.82
    WriteBarrier
    0.82
     IActionResult
    0.81
    DockStyle
    0.81
    viewDidLoad
    0.81
    IActionResult
    0.81
    PreferredItem
    0.81
    Activations Density 0.213%

    No Known Activations