© 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. 43668
    Prev
    Next
    INDEX
    Explanations

    {

    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
     Normdatei
    -0.73
    endphp
    -0.71
     intptr
    -0.67
    NUMX
    -0.64
    醐
    -0.63
     مشين
    -0.62
    tamol
    -0.62
    VIAF
    -0.59
    omene
    -0.57
    oneofs
    -0.57
    POSITIVE LOGITS
    httphttps
    0.51
    BitmapFactory
    0.51
     taas
    0.47
    Παραπομπές
    0.47
     poveznice
    0.46
    }")]
    0.45
     dětí
    0.44
     [][]
    0.43
     문서
    0.42
    
    0.42
    Activations Density 0.231%

    No Known Activations