© 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. 15481
    Prev
    Next
    INDEX
    Explanations

    LaTeX or mathematical notation elements

    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
     distanciation
    -0.73
     jsPsych
    -0.69
    ThroughAttribute
    -0.67
    tagHelperRunner
    -0.67
    hésite
    -0.65
    :✨
    -0.63
     Administrativna
    -0.61
     himo
    -0.61
     apellidos
    -0.59
    舺
    -0.59
    POSITIVE LOGITS
    ScopeManager
    0.65
    </em>
    0.64
    LogFactory
    0.57
    LoggerFactory
    0.55
    ArgsConstructor
    0.52
    [
    0.48
    …
    0.47
    …)
    0.46
     محفوظة
    0.46
    igshid
    0.45
    Activations Density 0.036%

    No Known Activations