© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 880
    Prev
    Next
    INDEX
    Explanations

    the word "can" followed by "be"

    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
    ########.
    -0.81
     posibil
    -0.71
    }());
    -0.68
     imposible
    -0.68
     Unable
    -0.68
     pageContext
    -0.68
     Egli
    -0.67
    would
    -0.66
    xxxxxx
    -0.66
    astéroïdes
    -0.66
    POSITIVE LOGITS
     can
    1.24
    can
    1.10
    Can
    1.06
     Can
    0.99
     CAN
    0.91
    CAN
    0.84
     cans
    0.81
     Cans
    0.80
    canActivate
    0.76
     Campan
    0.72
    Activations Density 0.343%

    No Known Activations