Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 14974
    Prev
    Next
    INDEX
    Explanations

    occurrences of mathematical functions and operations

    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
    cluse
    -0.62
    ագրություններ
    -0.57
    endpush
    -0.56
    MigrationBuilder
    -0.52
    actéristique
    -0.52
    setLabel
    -0.51
    stini
    -0.51
    Bain
    -0.51
    fonte
    -0.51
    日で
    -0.51
    POSITIVE LOGITS
    archiviato
    0.82
     كومونز
    0.71
     SwitchCompat
    0.67
    Nuorodos
    0.65
    zysta
    0.65
     BoxDecoration
    0.64
     LayoutInflater
    0.64
    arraycopy
    0.64
     Schuh
    0.63
     Pingback
    0.63
    Activations Density 0.003%

    No Known Activations