© 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. 5-CLT-HP
    7. 97918
    Prev
    Next
    INDEX
    Explanations

    skin

    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
     EDIT
    -0.42
     penurunan
    -0.41
     Winfield
    -0.40
     aço
    -0.40
     henkil
    -0.40
     Weight
    -0.40
     świad
    -0.39
     Sider
    -0.39
     tjen
    -0.38
     seier
    -0.37
    POSITIVE LOGITS
    +#+#
    0.96
     виправивши
    0.77
    Personensuche
    0.75
    ftagPool
    0.72
     كومونز
    0.71
    UnusedPrivate
    0.69
    NameInMap
    0.67
    Personendaten
    0.67
    TagMode
    0.67
    UpInside
    0.66
    Activations Density 0.000%

    No Known Activations