© 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. 42578
    Prev
    Next
    INDEX
    Explanations

    shown

    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
     shown
    -1.29
     Shown
    -1.16
    shown
    -1.12
     للاسماء
    -1.06
     الحره
    -1.02
     shewn
    -0.94
    Shown
    -0.90
    الحياه
    -0.89
    mybatisplus
    -0.88
    Personendaten
    -0.87
    POSITIVE LOGITS
     in
    0.60
    ,
    0.57
     unlikely
    0.51
    .
    0.51
     or
    0.51
    ish
    0.49
    1
    0.48
     that
    0.48
     this
    0.48
     get
    0.46
    Activations Density 0.062%

    No Known Activations