© 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. 22268
    Prev
    Next
    INDEX
    Explanations

    phrases encouraging experimentation or attempts at new activities

    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
     attempt
    -0.85
     attempts
    -0.84
     Attempt
    -0.81
     Olsen
    -0.77
     attempting
    -0.77
     Mocking
    -0.76
    مراجع
    -0.75
    attempts
    -0.75
    RenderAtEndOf
    -0.72
     Attempts
    -0.72
    POSITIVE LOGITS
    wamy
    0.60
     Trasp
    0.59
    fly
    0.58
    homonymie
    0.57
     propOrder
    0.57
    ority
    0.54
    ilkan
    0.54
    iteracy
    0.54
    wir
    0.54
    featureID
    0.54
    Activations Density 0.028%

    No Known Activations