© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14116
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "razor."

    oai_token-act-pair · gpt-4.1-nano
    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
    abstractmethod
    -0.59
     vuitton
    -0.58
     antaranya
    -0.54
    存于互联网档案馆
    -0.52
     strop
    -0.52
     avanti
    -0.51
    . 
    -0.51
     Terraria
    -0.51
    fattning
    -0.51
    iocene
    -0.50
    POSITIVE LOGITS
     riot
    1.51
     Riot
    1.09
     destined
    1.07
     riots
    1.02
     radiant
    0.97
     razor
    0.89
     Razor
    0.86
     Laplacian
    0.85
    Riot
    0.85
    riot
    0.82
    Activations Density 0.010%

    No Known Activations