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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 11065
    Prev
    Next
    INDEX
    Explanations

    references to "strips" or "strip" in various contexts

    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
     artistique
    -0.84
    zeitige
    -0.79
     الحره
    -0.77
     immobilier
    -0.77
    abestanden
    -0.76
    acionales
    -0.74
    vatar
    -0.72
    AsUp
    -0.72
    ly
    -0.71
     passés
    -0.71
    POSITIVE LOGITS
     Strip
    1.69
     STRIP
    1.68
     strip
    1.66
     Strips
    1.59
    Strip
    1.56
    strip
    1.56
     strips
    1.54
     stripped
    1.40
    STRIP
    1.39
     stripping
    1.33
    Activations Density 0.011%

    No Known Activations