© 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. 5-CLT-HP
    7. 759
    Prev
    Next
    INDEX
    Explanations

    waste and programming code

    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
     nahilalakip
    -0.88
    +#+#
    -0.75
     occaf
    -0.70
    expandindo
    -0.69
     purpoſe
    -0.69
    webElementGuid
    -0.66
     Majefty
    -0.66
     Brood
    -0.66
     fevere
    -0.65
     raiſ
    -0.64
    POSITIVE LOGITS
    CloseOperation
    0.50
    ########.
    0.43
    chevêque
    0.42
    subplots
    0.42
    send
    0.42
     Компа
    0.41
    ifikant
    0.40
     }^{(
    0.40
    ModelSerializer
    0.40
     Berikut
    0.40
    Activations Density 0.002%

    No Known Activations