© 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. 10219
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to assessments or studies

    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
     myſelf
    -1.05
    SerializedSize
    -0.90
     nakalista
    -0.88
     <>",
    -0.88
     itſelf
    -0.86
     himſelf
    -0.82
    giphy
    -0.81
    ulously
    -0.80
     Tann
    -0.79
    AlterField
    -0.79
    POSITIVE LOGITS
     http
    0.59
    RUNTIME
    0.55
    bahnhof
    0.54
    oppa
    0.54
     https
    0.53
     Valera
    0.51
    RBC
    0.50
    "\"
    0.49
    有过
    0.48
    TouchableOpacity
    0.48
    Activations Density 0.085%

    No Known Activations