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. 11838
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and comparisons involving values

    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
    LookAnd
    -0.91
    IntoConstraints
    -0.80
     CommandType
    -0.69
    AccessorTable
    -0.63
    uxxxx
    -0.61
     ویکی‌پدی
    -0.59
     незавершена
    -0.59
    AndEndTag
    -0.58
     ujednoznacz
    -0.57
    jetbrains
    -0.56
    POSITIVE LOGITS
     kultur
    0.48
    irdre
    0.48
    blender
    0.46
    ressible
    0.45
    ĵo
    0.45
    cokinetic
    0.44
     farinha
    0.43
    bės
    0.43
    conazole
    0.42
     balení
    0.42
    Activations Density 0.018%

    No Known Activations