© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16720
    Prev
    Next
    INDEX
    Explanations

    theorems and their applications within mathematical or logical 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
     propOrder
    -1.14
     myſelf
    -1.09
    ſelf
    -1.06
     itſelf
    -1.02
    ſelves
    -1.00
     Efq
    -0.97
     Jefus
    -0.96
     Chriftian
    -0.96
     Houſe
    -0.95
     purpoſe
    -0.94
    POSITIVE LOGITS
     A
    0.51
     (
    0.50
     [
    0.46
    ple
    0.46
     “
    0.46
     An
    0.45
     I
    0.43
     H
    0.43
     C
    0.43
     *
    0.42
    Activations Density 0.048%

    No Known Activations