© 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. 94039
    Prev
    Next
    INDEX
    Explanations

    what everything

    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
     everything
    -0.75
     whatever
    -0.68
     anything
    -0.66
     what
    -0.62
    whatever
    -0.53
    everything
    -0.48
    ']")
    -0.48
     tudo
    -0.45
    anything
    -0.44
     Everything
    -0.44
    POSITIVE LOGITS
     صوتيه
    0.99
    ftagPool
    0.87
     otomatig
    0.87
     estekak
    0.73
     survives
    0.73
    StoryboardSegue
    0.73
     qualifies
    0.71
    bootstrapcdn
    0.71
    webElementXpaths
    0.71
     defaultstate
    0.71
    Activations Density 0.018%

    No Known Activations