© 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. 22492
    Prev
    Next
    INDEX
    Explanations

    terms related to errors or anomalies in data analysis and research

    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
    GIVEREF
    -0.48
    rhosis
    -0.47
     못
    -0.47
     enf
    -0.46
     ogóle
    -0.46
    edia
    -0.44
    enged
    -0.43
    upta
    -0.43
    lobal
    -0.42
    intele
    -0.42
    POSITIVE LOGITS
    LookAnd
    0.85
     surla
    0.65
     cherchés
    0.62
    AsUp
    0.60
    Affirmed
    0.60
    \{\\
    0.56
    ^(@)
    0.56
    unknownFields
    0.54
     initComponents
    0.54
    verwijspagina
    0.54
    Activations Density 0.199%

    No Known Activations