© 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. 2726
    Prev
    Next
    INDEX
    Explanations

    words and numbers associated with American football

    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
    sella
    -0.48
     τά
    -0.47
    zusetzen
    -0.46
    اديم
    -0.46
     applied
    -0.45
     ordinateur
    -0.45
    formin
    -0.45
     apply
    -0.44
    Contributed
    -0.44
     APPLIED
    -0.44
    POSITIVE LOGITS
     catches
    1.09
     catching
    1.09
     catch
    1.07
     receivers
    1.06
     receiver
    1.01
     receptions
    0.95
     Catch
    0.93
    catch
    0.93
     RECE
    0.93
     Receiver
    0.92
    Activations Density 0.045%

    No Known Activations