© 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. 73206
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    ViewInit
    -0.52
    voo
    -0.46
    Pick
    -0.46
     Picking
    -0.46
    oust
    -0.45
     îna
    -0.45
    しまい
    -0.45
     NSCoder
    -0.45
    fiques
    -0.44
     paraître
    -0.44
    POSITIVE LOGITS
    StoryboardSegue
    0.78
     distinct
    0.71
    distinct
    0.65
    AutoField
    0.62
     remota
    0.58
     MotionEvent
    0.57
     Италијани
    0.56
     Distinct
    0.54
    twimg
    0.51
    oodoo
    0.50
    Activations Density 0.001%

    No Known Activations