© 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. 2522
    Prev
    Next
    INDEX
    Explanations

    the word "often" and common words surrounding it

    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
     potentially
    -0.88
     possibly
    -0.88
     essentially
    -0.73
     generally
    -0.73
     posiblemente
    -0.72
     basically
    -0.71
    potentially
    -0.70
    possibly
    -0.68
     hopefully
    -0.67
     normally
    -0.66
    POSITIVE LOGITS
     бывает
    0.88
    accompanied
    0.82
    DockStyle
    0.81
     accompanied
    0.78
    情况下
    0.76
     跳转至
    0.75
    accompag
    0.75
    цездатний
    0.74
    uffy
    0.73
    abestanden
    0.73
    Activations Density 0.554%

    No Known Activations