© 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. 18-RES-MATRYOSHKA-DC
    7. 500
    Prev
    Next
    INDEX
    Explanations

    the words "start", "begin", "initial" and words close to them in meaning or related.

    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.18.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.18.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
     שוליים
    -0.73
    bundet
    -0.66
    copyWith
    -0.65
    ïse
    -0.63
    LEncoder
    -0.63
    chappement
    -0.59
    führ
    -0.58
    rdı
    -0.57
    Viki
    -0.56
    honneur
    -0.55
    POSITIVE LOGITS
     afresh
    0.82
     anew
    0.82
    ต้น
    0.81
     starts
    0.76
     START
    0.73
    starts
    0.73
    START
    0.73
    Starts
    0.73
     시작
    0.73
     Begin
    0.71
    Activations Density 1.085%

    No Known Activations