© 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. 3-RES-MATRYOSHKA-DC
    7. 1558
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vastaan
    -0.64
     probabilmente
    -0.58
     fieltro
    -0.57
     mukana
    -0.57
     långt
    -0.56
     tasche
    -0.56
     fatica
    -0.56
     genoux
    -0.56
    miyor
    -0.55
     näin
    -0.55
    POSITIVE LOGITS
    <bos>
    0.66
     pleaſure
    0.65
    PhysRev
    0.61
    ArgsConstructor
    0.60
    DbType
    0.59
     WaitForSeconds
    0.58
    glPushMatrix
    0.58
     handleSubmit
    0.56
     Meksiku
    0.56
     ſtand
    0.55
    Activations Density 2.071%

    No Known Activations