© 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. 95177
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations

    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
     tube
    -0.77
    IMA
    -0.69
     Tube
    -0.68
    Citiți
    -0.68
     Sue
    -0.64
    Tube
    -0.63
     bArr
    -0.62
     Mait
    -0.62
    +#+
    -0.61
    urra
    -0.59
    POSITIVE LOGITS
    Personendaten
    0.75
    DockStyle
    0.63
    ViewFeatures
    0.60
     "..\..\..\
    0.57
     CreateTagHelper
    0.56
     laude
    0.52
     "..\..\
    0.51
     cadence
    0.47
    ticles
    0.46
     Réponses
    0.46
    Activations Density 0.114%

    No Known Activations