© 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. 4-CLT-HP
    7. 377
    Prev
    Next
    INDEX
    Explanations

    have

    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
     Theſe
    -0.57
    tagext
    -0.56
     IBOutlet
    -0.52
    ziná
    -0.51
    awtextra
    -0.51
    ariest
    -0.50
    setLayoutParams
    -0.50
    hütte
    -0.49
     essai
    -0.48
    riwal
    -0.47
    POSITIVE LOGITS
    енча
    0.58
    MLLoader
    0.54
    astéroïdes
    0.53
     Infórmanos
    0.52
     سكانية
    0.52
    UnsafeEnabled
    0.50
     telah
    0.49
     gezegd
    0.48
     Reverso
    0.48
     purport
    0.48
    Activations Density 0.020%

    No Known Activations