© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 173
    Prev
    Next
    INDEX
    Explanations

    references to statistical methods and analyses in research studies

    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
    zep
    -0.52
    mid
    -0.49
    ('.')
    -0.47
    ®
    -0.46
    zac
    -0.46
    Solu
    -0.46
     kid
    -0.45
    plom
    -0.45
     mid
    -0.44
    Solution
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.91
    GEBURTSDATUM
    0.88
    MigrationBuilder
    0.86
    rungsseite
    0.82
     propOrder
    0.81
    SharedCtor
    0.79
     factors
    0.79
     predictors
    0.77
     facteurs
    0.75
     AssemblyCulture
    0.73
    Activations Density 3.503%

    No Known Activations