© 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. 1172
    Prev
    Next
    INDEX
    Explanations

    the word "available" and words related to the state of being

    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
    Autoritní
    -0.86
    utnik
    -0.73
    AddTagHelper
    -0.71
    endphp
    -0.68
    робнее
    -0.68
    RuleContext
    -0.67
    gdx
    -0.66
     oleh
    -0.66
    GeoNames
    -0.65
    thansa
    -0.65
    POSITIVE LOGITS
    exists
    0.56
     disponible
    0.54
    available
    0.52
     dư
    0.51
    availability
    0.50
     available
    0.48
     availability
    0.48
    Available
    0.47
    Dispon
    0.47
     Exists
    0.46
    Activations Density 0.682%

    No Known Activations