© 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. 923
    Prev
    Next
    INDEX
    Explanations

    the

    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
    曖昧さ回避
    -0.76
    BibitemShut
    -0.66
    Datuak
    -0.64
    AutoresizingMask
    -0.63
     мәкал
    -0.63
     Anſ
    -0.59
     سكانية
    -0.58
    #+#
    -0.58
    +#+#
    -0.57
    entance
    -0.57
    POSITIVE LOGITS
    AddTagHelper
    0.73
     long
    0.59
     MainAxisSize
    0.50
     AttributeSet
    0.47
    long
    0.44
     долго
    0.44
    idual
    0.42
    пьютер
    0.42
     patients
    0.42
     many
    0.42
    Activations Density 0.001%

    No Known Activations