© 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. 28413
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to structured or formatted data

    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
     صوتيه
    -0.83
     فريبيس
    -0.70
    Портал
    -0.65
    WithMany
    -0.64
    permum
    -0.63
    CloseOperation
    -0.62
    weile
    -0.59
     муніципалі
    -0.57
    BITDA
    -0.56
    remia
    -0.55
    POSITIVE LOGITS
     Paglinawan
    0.81
    Personensuche
    0.63
    FunctionFlags
    0.55
    DockStyle
    0.53
    ThroughAttribute
    0.53
    MigrationBuilder
    0.52
     näin
    0.52
    下载附件
    0.47
    вающих
    0.47
     cohomology
    0.46
    Activations Density 0.295%

    No Known Activations