© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15468
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and evaluations about items, emphasizing preferences and quality

    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
    DOCTYPE
    -0.47
    tabular
    -0.47
    manship
    -0.44
     equipo
    -0.44
    @
    -0.43
    StoryboardSegue
    -0.42
    terase
    -0.40
     @
    -0.40
    pushFollow
    -0.40
     EQUIPMENT
    -0.39
    POSITIVE LOGITS
     مشين
    0.69
    日閲覧
    0.68
    Rüyada
    0.65
    ГЛА
    0.65
     ***!
    0.65
     dépens
    0.64
    GEBURTSDATUM
    0.64
    LookAnd
    0.62
     tebal
    0.62
    Diweddarwch
    0.62
    Activations Density 0.019%

    No Known Activations