© 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. 5054
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     >=",
    -0.91
    脚注の使い方
    -0.79
    ագրություններ
    -0.75
    Personendaten
    -0.74
    ^(@)
    -0.74
     disambiguazione
    -0.70
    tvguidetime
    -0.68
    NUMX
    -0.68
    MessageOf
    -0.65
     FormGroup
    -0.65
    POSITIVE LOGITS
    何より
    0.48
    нося
    0.43
     ۱۳۸
    0.40
    lichem
    0.39
     Immune
    0.39
    sworth
    0.38
    ktı
    0.37
     subject
    0.37
     merec
    0.37
     ۱۳۹
    0.37
    Activations Density 0.003%

    No Known Activations