© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3493
    Prev
    Next
    INDEX
    Explanations

    had

    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
    ところで
    -0.65
    навли
    -0.52
    prnewswire
    -0.51
    ToReturn
    -0.49
    peaks
    -0.47
     peak
    -0.47
    └──
    -0.46
     '=',
    -0.45
    τεί
    -0.45
     nowhere
    -0.44
    POSITIVE LOGITS
     مشين
    0.78
     ProtoMessage
    0.77
     Walkover
    0.75
     HasFactory
    0.71
     betweenstory
    0.68
    DebuggerStep
    0.67
    StoryboardSegue
    0.66
     intptr
    0.66
    ########.
    0.64
     ब्रेकडाउन
    0.63
    Activations Density 0.007%

    No Known Activations