© 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. 16773
    Prev
    Next
    INDEX
    Explanations

    punctuations and quotation marks in academic writing

    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
     שוליים
    -0.71
     disambiguazione
    -0.68
     Workmen
    -0.60
     Efq
    -0.59
    exitRule
    -0.58
     Pauli
    -0.57
    WithIOException
    -0.55
    ніципалі
    -0.55
     tyme
    -0.55
     يتيمه
    -0.54
    POSITIVE LOGITS
    IMPORTED
    0.65
     seura
    0.58
    getActiveSheet
    0.56
    ACITY
    0.56
    __':
    0.54
     Bl
    0.53
     كومونز
    0.53
    ]='\
    0.53
     gruesa
    0.52
    )$_
    0.52
    Activations Density 0.008%

    No Known Activations