© 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. 91
    Prev
    Next
    INDEX
    Explanations

    numerical expressions, particularly those related to ranges or measurements

    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
     (
    -0.68
     in
    -0.63
     B
    -0.59
     has
    -0.59
    ,
    -0.59
    .
    -0.57
     C
    -0.57
     at
    -0.57
     O
    -0.56
     “
    -0.56
    POSITIVE LOGITS
     Monfieur
    1.29
     myſelf
    1.23
     Efq
    1.20
     Majefty
    1.16
     pleaſure
    1.16
     faſt
    1.15
     ſever
    1.13
     Theſe
    1.13
     fevere
    1.10
     ſeveral
    1.09
    Activations Density 2.482%

    No Known Activations