© 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. 1415
    Prev
    Next
    INDEX
    Explanations

    negations and intensifiers

    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
     <<<<<<<<<<<<<<
    -0.53
     either
    -0.52
     any
    -0.51
     volon
    -0.50
     Noord
    -0.50
    uesa
    -0.48
     سبورت
    -0.48
     hyvin
    -0.48
     cualquiera
    -0.48
     någon
    -0.46
    POSITIVE LOGITS
     fathom
    0.79
     BELIEVE
    0.77
    ArrowToggle
    0.76
    AsUp
    0.74
    Personensuche
    0.73
     believe
    0.71
    believe
    0.69
    fjspx
    0.68
     afford
    0.68
     Мексичка
    0.66
    Activations Density 0.208%

    No Known Activations