© 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. 10305
    Prev
    Next
    INDEX
    Explanations

    verbs and verb phrases, particularly those associated with actions and changes

    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
    .
    -0.59
     werde
    -0.43
    ど
    -0.42
    workbench
    -0.42
    umoj
    -0.41
    !
    -0.41
    的她
    -0.41
    am
    -0.40
    شان
    -0.40
    ;
    -0.40
    POSITIVE LOGITS
     الرياضيه
    0.88
    出版年
    0.88
    ftagPool
    0.84
    XmlAccessorType
    0.79
     незавершена
    0.79
     raiſ
    0.79
     iſt
    0.79
     purpoſe
    0.78
    CodeAttribute
    0.77
    styleType
    0.77
    Activations Density 0.296%

    No Known Activations