© 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. 4410
    Prev
    Next
    INDEX
    Explanations

    see

    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
     переписи
    -0.44
    ніципалі
    -0.44
     censi
    -0.42
    @[+][
    -0.42
     pinulongan
    -0.40
    regation
    -0.40
    ODI
    -0.39
     beginnetje
    -0.39
    Namara
    -0.38
     AssemblyTitle
    -0.38
    POSITIVE LOGITS
     if
    1.09
    if
    0.88
     jika
    0.76
    jika
    0.75
     If
    0.75
    If
    0.73
     dacă
    0.70
     IF
    0.68
     kalau
    0.68
     nếu
    0.68
    Activations Density 0.003%

    No Known Activations