© 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. 22-RES-MATRYOSHKA-DC
    7. 2263
    Prev
    Next
    INDEX
    Explanations

    periods

    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
    ympto
    -0.55
    Distribuzione
    -0.50
    ​
    -0.48
    .
    -0.47
     насељу
    -0.47
    Coordonnées
    -0.46
    nalités
    -0.46
    {{$
    -0.44
    tldr
    -0.44
    angani
    -0.44
    POSITIVE LOGITS
     незавершена
    0.78
    findpost
    0.72
    mybatisplus
    0.71
    AddHtmlAttribute
    0.69
    bootstrapcdn
    0.66
     بيها
    0.66
    GraphicsUnit
    0.64
    ᐟ
    0.64
    sendLogPayload
    0.61
    LookAnd
    0.60
    Activations Density 0.759%

    No Known Activations