© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 230
    Prev
    Next
    INDEX
    Explanations

    helper verbs like can, will, and to.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     специально
    -0.56
    "}";
    -0.55
    rinfo
    -0.54
    adpleegd
    -0.54
    styleType
    -0.54
    شهاد
    -0.53
    watching
    -0.52
    Ask
    -0.52
    出版年
    -0.52
    raging
    -0.51
    POSITIVE LOGITS
     successfully
    1.52
     succeed
    1.42
     achieve
    1.41
     achieving
    1.33
     succeeded
    1.29
     succeeds
    1.29
     successful
    1.28
     achieves
    1.27
     achieved
    1.23
     Successfully
    1.22
    Activations Density 3.777%

    No Known Activations