© 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. 20-CLT-HP
    7. 77707
    Prev
    Next
    INDEX
    Explanations

    documentation or code snippets

    np_max-act-logits · 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
    ValueStyle
    -0.72
    Vidite
    -0.67
    contentLoaded
    -0.59
    mybatisplus
    -0.56
     незавершена
    -0.54
    laterra
    -0.53
    nocache
    -0.52
    السكان
    -0.51
    picasso
    -0.50
    ergies
    -0.50
    POSITIVE LOGITS
    ChildScrollView
    0.66
     hard
    0.56
    rawDesc
    0.52
     harder
    0.48
     hardest
    0.47
     Lauf
    0.47
    __(/*!
    0.46
     hardness
    0.44
    matory
    0.43
    ICIÓN
    0.43
    Activations Density 0.000%

    No Known Activations