© 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. 15477
    Prev
    Next
    INDEX
    Explanations

    phrases related to playoff contention or sports performance

    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
    __":
    -0.81
    FunctionFlags
    -0.80
    QMetaType
    -0.76
    ThroughAttribute
    -0.76
    __':
    -0.70
    transQ
    -0.68
    PerformLayout
    -0.67
    styleType
    -0.67
    Rüyada
    -0.67
    RTEE
    -0.66
    POSITIVE LOGITS
    slidesPer
    0.40
    ضاء
    0.39
    algo
    0.39
     suspe
    0.38
     race
    0.38
     zaw
    0.38
     wanted
    0.37
    race
    0.37
    ideos
    0.36
    鞍
    0.36
    Activations Density 0.038%

    No Known Activations