© 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. 28494
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial or temporal 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
     كومونز
    -0.67
    WillAppear
    -0.55
    PhysRevLett
    -0.53
    createStatement
    -0.50
    LabelTagHelper
    -0.50
    soka
    -0.50
     کیلوم
    -0.49
    stddef
    -0.49
    пенно
    -0.48
    :✨
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.83
     transférez
    0.68
    发表于
    0.65
     blessé
    0.64
     auroit
    0.60
     chré
    0.59
     religieux
    0.58
     discorso
    0.58
     partag
    0.57
     béné
    0.57
    Activations Density 0.264%

    No Known Activations