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. 8549
    Prev
    Next
    INDEX
    Explanations

    references to automated code generation tools and Microsoft technologies

    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
     fédé
    -0.48
     partag
    -0.46
     ruota
    -0.45
    unknownFields
    -0.43
    altezza
    -0.43
     Jérusalem
    -0.42
     BoxDecoration
    -0.42
    tól
    -0.42
     schéma
    -0.40
    خول
    -0.40
    POSITIVE LOGITS
    NameInMap
    1.09
    LookAnd
    0.90
    Personensuche
    0.88
     estekak
    0.88
    TagMode
    0.87
    帖最后由
    0.86
    ⓧ
    0.82
    Personendaten
    0.79
     Roskov
    0.78
    hoeddwyd
    0.77
    Activations Density 0.013%

    No Known Activations