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. 8835
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to genetic testing and analysis

    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
    awtextra
    -0.56
    ksin
    -0.47
     romans
    -0.45
    ORO
    -0.44
    athers
    -0.42
    ∬
    -0.42
     fra
    -0.42
     adop
    -0.42
     mang
    -0.42
    ables
    -0.42
    POSITIVE LOGITS
    loài
    0.86
     Offisielt
    0.77
    .*")]
    0.77
    KURZBESCHREIBUNG
    0.75
    Referències
    0.73
     كومونز
    0.73
    RenderAtEndOf
    0.73
    Manbalar
    0.71
    verwijspagina
    0.71
     AssemblyVersion
    0.69
    Activations Density 0.060%

    No Known Activations