© 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. 2720
    Prev
    Next
    INDEX
    Explanations

    and

    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
    felves
    -0.74
     للمعارف
    -0.64
     themſelves
    -0.61
    .');
    -0.60
     magasiner
    -0.59
     --;
    -0.58
    — 
    -0.58
     OGSÅ
    -0.58
     himſelf
    -0.57
    ^(@)
    -0.57
    POSITIVE LOGITS
    setVerticalGroup
    0.66
    SharedDtor
    0.54
    adaptiveStyles
    0.54
    CDCl
    0.54
     resourceCulture
    0.52
    AndEndTag
    0.49
     cannot
    0.47
     betweenstory
    0.46
     taxed
    0.46
    ulateur
    0.45
    Activations Density 0.014%

    No Known Activations