© 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. 32131
    Prev
    Next
    INDEX
    Explanations

    references to the concept of ability or capabilities

    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
     }}"></
    -0.88
     Fros
    -0.73
     Ramona
    -0.72
    SECUR
    -0.69
     }</
    -0.68
     Stapleton
    -0.68
    Портал
    -0.66
     inconclusive
    -0.65
    onedDateTime
    -0.65
    〢
    -0.64
    POSITIVE LOGITS
     abilities
    0.84
    createClass
    0.81
     ability
    0.79
     opérateur
    0.78
    +#+#
    0.77
     Abilities
    0.72
    skills
    0.70
    FormTagHelper
    0.69
     skill
    0.68
    skill
    0.68
    Activations Density 0.013%

    No Known Activations