© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43095
    Prev
    Next
    INDEX
    Explanations

    Ner

    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
     Ner
    -1.32
    Ner
    -1.08
    RenderAtEndOf
    -0.94
    évaluateur
    -0.82
    gameserver
    -0.79
     Савезне
    -0.75
    PYX
    -0.71
    Vidite
    -0.71
    ソッド
    -0.70
    liesslich
    -0.69
    POSITIVE LOGITS
    localScale
    0.47
     stá
    0.44
    antal
    0.42
    ню
    0.42
    riga
    0.40
    rens
    0.40
    атра
    0.40
    ither
    0.40
    schemas
    0.40
    атр
    0.40
    Activations Density 1.731%

    No Known Activations