© 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. 91673
    Prev
    Next
    INDEX
    Explanations

    asterisk

    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
    原始内容存档于
    -0.78
    WithIOException
    -0.75
     незавершена
    -0.74
    Abitanti
    -0.72
     nahilalakip
    -0.71
    httphttps
    -0.68
    +/**
    -0.66
    ResumeLayout
    -0.65
    NameInMap
    -0.64
    WebVitals
    -0.64
    POSITIVE LOGITS
     houver
    0.48
    versaries
    0.43
    NOPQRST
    0.41
     tolerancia
    0.41
    oluted
    0.40
    ECES
    0.39
    stol
    0.39
    assung
    0.38
    cumulative
    0.38
     annulus
    0.38
    Activations Density 0.007%

    No Known Activations