© 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. 119
    Prev
    Next
    INDEX
    Explanations

    references to various scientific or mathematical parameters and conditions

    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
     Shakspeare
    -0.80
     linkovi
    -0.78
    aarrggbb
    -0.75
    antMatchers
    -0.72
    AsUp
    -0.69
    bootstrapcdn
    -0.68
     Shaksp
    -0.66
    OGND
    -0.65
    الإنجليزية
    -0.63
    ientôt
    -0.63
    POSITIVE LOGITS
     ujednoznacz
    0.63
    rungsseite
    0.60
     noted
    0.56
     note
    0.53
     recent
    0.53
    MathML
    0.53
     reason
    0.52
    ']));
    0.49
     noteworthy
    0.49
    getDescription
    0.49
    Activations Density 18.089%

    No Known Activations