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. 26838
    Prev
    Next
    INDEX
    Explanations

    the presence of numeric values or mathematical symbols

    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
     Hom
    -0.49
    íslu
    -0.48
    Hom
    -0.48
     sentral
    -0.47
    eral
    -0.46
    полага
    -0.45
    んな
    -0.44
    '
    -0.43
    createElement
    -0.42
    getElementById
    -0.42
    POSITIVE LOGITS
     beginnetje
    0.86
    Viitteet
    0.82
     ujednoznacz
    0.81
    oredCriteria
    0.80
    AndEndTag
    0.78
     ContentValues
    0.77
    MigrationBuilder
    0.75
    abestanden
    0.74
    GEBURTSDATUM
    0.74
    XmlAccessorType
    0.73
    Activations Density 0.004%

    No Known Activations