© 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. 225
    Prev
    Next
    INDEX
    Explanations

    statements regarding the identification and evaluation of processes or conditions in various contexts, particularly emphasizing accuracy and significance

    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
     raiſ
    -1.01
     purpoſe
    -0.96
     autorytatywna
    -0.95
     Theſe
    -0.94
     houſe
    -0.93
     uſed
    -0.93
    ⓧ
    -0.92
     Efq
    -0.91
     Anſ
    -0.91
     preſent
    -0.90
    POSITIVE LOGITS
     is
    0.56
    <eos>
    0.49
    htdocs
    0.47
     I
    0.43
     program
    0.43
    XmlAccessType
    0.43
     [
    0.43
    urs
    0.40
    таж
    0.40
     i
    0.40
    Activations Density 1.175%

    No Known Activations