© 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. 20-CLT-HP
    7. 75989
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · 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
    ParallelGroup
    -0.49
     Feliz
    -0.48
     Fibre
    -0.48
    withIdentifier
    -0.47
     ningún
    -0.46
     fortun
    -0.44
     Quince
    -0.44
    astia
    -0.44
    illam
    -0.44
    ěn
    -0.44
    POSITIVE LOGITS
     Chwiliwch
    0.73
    ьаж
    0.54
    #+#
    0.54
    +#+#
    0.52
     parseFrom
    0.52
     sẻ
    0.52
    曖昧さ回避
    0.51
     MutableLiveData
    0.51
     OGSÅ
    0.49
     bezeichneter
    0.49
    Activations Density 0.003%

    No Known Activations