© 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. 4-CLT-HP
    7. 2013
    Prev
    Next
    INDEX
    Explanations

    awards recognition

    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
    parsedMessage
    -0.65
     صوتيه
    -0.58
    PerformLayout
    -0.58
    IsContent
    -0.57
    Greet
    -0.55
     InputDecoration
    -0.54
    ंदीखरीदारी
    -0.54
    InitVars
    -0.54
     فريبيس
    -0.53
    PrototypeOf
    -0.52
    POSITIVE LOGITS
     StringTokenizer
    0.58
     gyhoeddwyd
    0.54
    NullCheck
    0.54
    <?=
    0.52
     manutenzione
    0.51
     enough
    0.50
     äta
    0.50
    PhysRevLett
    0.49
     beaucoup
    0.49
     little
    0.49
    Activations Density 0.006%

    No Known Activations