Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30699
    Prev
    Next
    INDEX
    Explanations

    the word "tight" and morphological variations of that word

    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
    Solu
    -0.68
     pans
    -0.66
     Katz
    -0.64
     Gale
    -0.64
    trino
    -0.63
    shel
    -0.63
     kab
    -0.61
    Zelda
    -0.61
     stoned
    -0.60
     MSR
    -0.60
    POSITIVE LOGITS
     Tight
    1.77
    Tight
    1.75
     tight
    1.73
    tight
    1.67
     tightness
    1.51
     tighter
    1.48
     tighten
    1.32
     tightly
    1.31
     tightened
    1.24
     tightening
    1.20
    Activations Density 0.006%

    No Known Activations