© 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. 13837
    Prev
    Next
    INDEX
    Explanations

    adjectives and their variations that indicate value or suitability

    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
    Negative Logits
     @"/
    -0.70
    rungsseite
    -0.68
    +#+
    -0.68
    ########.
    -0.67
    Personendaten
    -0.67
    IsMutable
    -0.66
    LLocation
    -0.66
    SharedDtor
    -0.65
    Datuak
    -0.65
    SOUNDBITE
    -0.63
    POSITIVE LOGITS
    tinyos
    0.63
     Ediciones
    0.57
     dites
    0.56
     posteriores
    0.53
    gup
    0.51
     nicio
    0.50
     ulang
    0.49
     lạ
    0.49
     aparente
    0.48
     zuvor
    0.48
    Activations Density 0.076%

    No Known Activations