© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40633
    Prev
    Next
    INDEX
    Explanations

    LM, GE

    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
    aff
    -0.51
     LM
    -0.45
     GE
    -0.43
     Better
    -0.41
    LM
    -0.39
     TOS
    -0.39
    Aff
    -0.38
     cond
    -0.38
    MTA
    -0.38
     Imp
    -0.37
    POSITIVE LOGITS
    PyExc
    0.84
     ivelany
    0.79
     defaultstate
    0.76
    dhury
    0.71
    principalTable
    0.70
    ResumeLayout
    0.69
     '\\;'
    0.69
     requestCode
    0.67
    ieza
    0.66
    IndentedString
    0.66
    Activations Density 0.079%

    No Known Activations