© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 29492
    Prev
    Next
    INDEX
    Explanations

    tests related to error handling in function inputs

    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
     esternos
    -0.59
     OMITBAD
    -0.53
    Referències
    -0.52
     للمعارف
    -0.52
    resave
    -0.50
    ?>">
    -0.50
    ValueGeneration
    -0.49
    inking
    -0.49
    rotum
    -0.48
     restTemplate
    -0.47
    POSITIVE LOGITS
     propOrder
    0.81
    atég
    0.60
    ibatis
    0.59
    InSection
    0.52
     Charging
    0.52
    msgTypes
    0.51
    ukunfts
    0.51
    AlterField
    0.50
     lädt
    0.50
    criture
    0.49
    Activations Density 0.051%

    No Known Activations