© 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. 5-CLT-HP
    7. 586
    Prev
    Next
    INDEX
    Explanations

    Code and technical descriptions

    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
    InSection
    -0.88
    enumii
    -0.75
    audiovisuel
    -0.71
    期刊论文
    -0.71
     AssemblyCompany
    -0.69
    endpush
    -0.69
    SequentialGroup
    -0.69
    PerformLayout
    -0.68
    مراجع
    -0.67
    IntoConstraints
    -0.66
    POSITIVE LOGITS
    PostMapping
    0.52
    ism
    0.49
     edge
    0.44
    ismo
    0.43
     препратки
    0.42
     edges
    0.42
    ismu
    0.42
     EDGE
    0.41
    yh
    0.41
     Finalmente
    0.41
    Activations Density 0.001%

    No Known Activations