© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1143
    Prev
    Next
    INDEX
    Explanations

    string of numbers separated by commas

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    Configurer
    -0.65
    BASEPATH
    -0.52
    Viited
    -0.47
     Alcalde
    -0.47
     vane
    -0.47
     MOQ
    -0.46
    曖昧さ回避
    -0.46
     anyag
    -0.45
    opsida
    -0.45
    #+#
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.97
     '\\;'
    0.93
    Personendaten
    0.89
     فريبيس
    0.76
    \}}
    0.72
     BoxDecoration
    0.69
    aarrggbb
    0.67
     ?></
    0.66
    GEBURTSDATUM
    0.65
    addCriterion
    0.64
    Activations Density 1.770%

    No Known Activations