© 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. 18-RES-MATRYOSHKA-DC
    7. 879
    Prev
    Next
    INDEX
    Explanations

    mentions of rules or laws.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    tagHelperRunner
    -0.84
    KommentareTeilen
    -0.58
    +</
    -0.57
    .='
    -0.57
     '{@
    -0.57
    endsection
    -0.56
    HideFlags
    -0.55
     candidatura
    -0.54
     Abschnitt
    -0.54
     resourceCulture
    -0.54
    POSITIVE LOGITS
     Rules
    1.43
     rules
    1.37
     RULES
    1.29
    Rules
    1.27
    rules
    1.26
     rule
    1.24
     Rule
    1.23
     RULE
    1.23
    RULES
    1.12
    rule
    1.10
    Activations Density 0.247%

    No Known Activations