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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38373
    Prev
    Next
    INDEX
    Explanations

    words ending in "able"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asible
    -3.13
    asibility
    -1.44
    asable
    -0.85
     يتيمه
    -0.82
    feasible
    -0.78
    CFLAGS
    -0.77
    PreferredItem
    -0.75
    riwal
    -0.74
    +#+#
    -0.73
     CommonModule
    -0.70
    POSITIVE LOGITS
    ments
    0.48
     enough
    0.46
     emb
    0.44
    own
    0.44
     to
    0.43
    awtextra
    0.43
    truct
    0.42
    ykite
    0.41
    aged
    0.40
    md
    0.40
    Activations Density 1.410%

    No Known Activations