© 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. 3358
    Prev
    Next
    INDEX
    Explanations

    he

    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
    出版年
    -0.94
    Filler
    -0.65
    mmation
    -0.60
    phane
    -0.60
    IDF
    -0.58
    Stride
    -0.58
    aryen
    -0.56
    oxane
    -0.56
     //$
    -0.56
    idf
    -0.55
    POSITIVE LOGITS
    RenderAtEndOf
    0.82
    까지
    0.40
    GetKeyDown
    0.40
    Personendaten
    0.39
    ここまで
    0.38
     there
    0.37
     fairness
    0.35
    there
    0.35
    そこは
    0.34
     noon
    0.34
    Activations Density 0.011%

    No Known Activations