© 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. 25
    Prev
    Next
    INDEX
    Explanations

    letters and symbols, particularly those associated with variables in mathematical expressions

    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
    iformis
    -0.50
    SPECIFIED
    -0.48
     mutually
    -0.48
     EVANS
    -0.47
    SCHEMA
    -0.47
     informar
    -0.47
    irmed
    -0.46
     مشين
    -0.46
     chronological
    -0.46
     Belly
    -0.46
    POSITIVE LOGITS
    djangoproject
    0.84
    brainly
    0.75
    ]")]
    0.75
    RenderAtEndOf
    0.74
    queryInterface
    0.73
    kloped
    0.73
    Referanser
    0.72
    хьтан
    0.71
    ']")
    0.69
     tartalomajánló
    0.69
    Activations Density 1.572%

    No Known Activations