© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21522
    Prev
    Next
    INDEX
    Explanations

    scientific results and methods related to cellular processes and their implications 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
    stylesheet
    -0.43
     ángel
    -0.43
     Благодаря
    -0.42
    łgorzata
    -0.42
     sostuvo
    -0.41
     sond
    -0.41
     dimenti
    -0.40
    zeera
    -0.40
     JSTOR
    -0.40
     anjo
    -0.40
    POSITIVE LOGITS
     الحره
    0.85
     actionMode
    0.77
    ThroughAttribute
    0.66
    )++;
    0.62
    CompilerServices
    0.60
    principalColumn
    0.60
    pulumi
    0.60
    cephala
    0.60
    νώ
    0.59
    +][
    0.59
    Activations Density 0.258%

    No Known Activations