© 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. 93951
    Prev
    Next
    INDEX
    Explanations

    animals or technical writing

    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
     itſelf
    -0.88
     TextInputType
    -0.87
     anún
    -0.84
     dunes
    -0.83
     dieux
    -0.81
     MainAxisSize
    -0.81
     normaux
    -0.81
     zelve
    -0.79
    seamnă
    -0.79
     myſelf
    -0.79
    POSITIVE LOGITS
    ing
    0.65
     er
    0.63
     or
    0.62
    ,
    0.62
    .
    0.59
     che
    0.58
     ang
    0.57
     der
    0.56
     sta
    0.56
     in
    0.53
    Activations Density 1.577%

    No Known Activations