© 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. 1-CLT-HP
    7. 11343
    Prev
    Next
    INDEX
    Explanations

    public matters

    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
    awtextra
    -0.64
    ecore
    -0.63
    håll
    -0.60
    Datuak
    -0.59
     Majefty
    -0.57
    ntö
    -0.57
    UnsafeEnabled
    -0.57
    يكب
    -0.57
    intios
    -0.57
    */;
    -0.56
    POSITIVE LOGITS
     OnInit
    0.55
     оригіналу
    0.54
     ElementRef
    0.48
    สติ
    0.48
     of
    0.48
    imbawa
    0.48
    ArgumentParser
    0.44
     j
    0.43
     miss
    0.42
    ệc
    0.42
    Activations Density 0.014%

    No Known Activations