© 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. 9750
    Prev
    Next
    INDEX
    Explanations

    different strategies and measures related to implementation in various 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
    fontWeight
    -0.49
    drawText
    -0.47
     aDecoder
    -0.43
    Scénario
    -0.42
    {
    -0.42
     including
    -0.41
    ront
    -0.41
     related
    -0.41
     work
    -0.39
     sick
    -0.39
    POSITIVE LOGITS
    Jeografia
    0.84
     ProtoMessage
    0.78
    OGND
    0.75
    adaptiveStyles
    0.69
    GOTREF
    0.67
    WithMany
    0.65
    ########.
    0.65
    StructEnd
    0.64
    MigrationBuilder
    0.63
    SequentialGroup
    0.63
    Activations Density 0.260%

    No Known Activations