© 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. 5789
    Prev
    Next
    INDEX
    Explanations

    interests

    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
    Portale
    -0.57
    mitian
    -0.52
    <#
    -0.51
    fillText
    -0.51
     Release
    -0.50
     Voulez
    -0.50
     Act
    -0.50
    嘧
    -0.48
     RELEASE
    -0.48
     Grant
    -0.47
    POSITIVE LOGITS
    PreferredItem
    0.60
     المعيارى
    0.56
     cherchés
    0.53
    toluene
    0.52
    ίναι
    0.51
     Petron
    0.51
     nahilalakip
    0.49
    الحياه
    0.49
    Gruß
    0.49
     frattempo
    0.48
    Activations Density 0.001%

    No Known Activations