© 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. 5-CLT-HP
    7. 5927
    Prev
    Next
    INDEX
    Explanations

    code

    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
     يتيمه
    -0.64
    GenerationType
    -0.62
     gynhyrchwyd
    -0.58
    WithMany
    -0.51
     gradova
    -0.47
    تقاوى
    -0.47
    ỏa
    -0.46
    rophe
    -0.46
    hamm
    -0.46
    ambi
    -0.45
    POSITIVE LOGITS
    DebuggerNonUser
    0.56
     Eraser
    0.56
     AppModule
    0.53
     Runoff
    0.51
     Classroom
    0.51
    वरण
    0.50
     eventdata
    0.49
    bufio
    0.49
    #
    0.48
     eraser
    0.48
    Activations Density 0.005%

    No Known Activations