© 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. 25059
    Prev
    Next
    INDEX
    Explanations

    programming constructs, particularly variable assignments and method signatures

    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
    Negative Logits
     CreateTagHelper
    -0.63
    WithMany
    -0.47
    StoryboardSegue
    -0.47
    chainId
    -0.44
     ModelExpression
    -0.43
     JpaRepository
    -0.43
    Normdaten
    -0.42
     Name
    -0.42
     namin
    -0.42
    glBegin
    -0.41
    POSITIVE LOGITS
    Aktualisiert
    0.64
    তথ্যসূত্র
    0.64
    qrstuvwxyz
    0.63
     itſelf
    0.63
    Дереккөздер
    0.63
    FieldDescriptor
    0.61
     članak
    0.61
    ksikon
    0.61
    Commentaires
    0.59
    Filmografie
    0.58
    Activations Density 0.158%

    No Known Activations