© 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. 32075
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limitations and constraints in data or methodologies

    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
     cận
    -0.60
     الحره
    -0.51
    stdio
    -0.48
     acest
    -0.47
     even
    -0.47
    ensos
    -0.46
     Waren
    -0.44
    meto
    -0.43
     付
    -0.43
    tenis
    -0.43
    POSITIVE LOGITS
    AxisAlignment
    0.82
    RegressionTest
    0.71
     MainAxisSize
    0.70
    IndentedString
    0.67
     برانيه
    0.63
    LookAnd
    0.63
     GetEnumerator
    0.61
    onets
    0.61
    يكب
    0.61
     متعلقه
    0.60
    Activations Density 0.101%

    No Known Activations