© 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. 14931
    Prev
    Next
    INDEX
    Explanations

    numerical values and percentages in the context of statistical data

    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
     pengh
    -0.46
    clearInterval
    -0.42
    سوب
    -0.42
     to
    -0.42
     indoss
    -0.42
    <
    -0.40
    ellä
    -0.40
     and
    -0.39
     daß
    -0.38
    subpackage
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    1.06
     المعيارى
    1.05
    matchCondition
    1.02
    LookAnd
    1.02
    setVerticalGroup
    0.99
     otomatig
    0.98
     intptr
    0.96
    Personendaten
    0.96
    oredCriteria
    0.93
    UnusedPrivate
    0.91
    Activations Density 0.010%

    No Known Activations