© 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. 24-RES-MATRYOSHKA-DC
    7. 215
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate spam or advertising content and also possibly short Italian fragments.

    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.24.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.24.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
     Mongols
    -0.57
     kurzem
    -0.55
    ándola
    -0.53
     Schicksal
    -0.51
    ándolos
    -0.51
    ഏ
    -0.51
    ädchen
    -0.51
     Communists
    -0.50
     nichts
    -0.50
    billed
    -0.50
    POSITIVE LOGITS
     già
    0.55
     delle
    0.54
     più
    0.52
     sempre
    0.51
     di
    0.49
     anche
    0.47
     della
    0.47
     nella
    0.46
     come
    0.45
     dell
    0.45
    Activations Density 0.213%

    No Known Activations