© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8981
    Prev
    Next
    INDEX
    Explanations

    terms related to spelling and spell-checking functions

    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
    anadium
    -0.80
    Referències
    -0.74
    >>>>>>>>
    -0.71
    jsonwebtoken
    -0.66
    JsonPropertyName
    -0.66
     propOrder
    -0.66
    btnClose
    -0.65
     AspNetCore
    -0.64
    Clik
    -0.62
    pretation
    -0.61
    POSITIVE LOGITS
     spell
    1.34
     Spell
    1.30
     spells
    1.27
    spell
    1.22
    Spell
    1.20
     Spelling
    1.20
     Spells
    1.17
     spelling
    1.15
    Spelling
    1.07
    SPELL
    1.07
    Activations Density 0.003%

    No Known Activations