© 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. 1-CLT-HP
    7. 45911
    Prev
    Next
    INDEX
    Explanations

    needs

    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
    ⓧ
    -0.68
    i
    -0.58
     समीक्षाएं
    -0.58
    tro
    -0.56
    tub
    -0.56
    ik
    -0.56
    sa
    -0.56
    ings
    -0.55
    sp
    -0.54
    san
    -0.53
    POSITIVE LOGITS
    voici
    0.55
    ",@"
    0.51
    LLocation
    0.51
     invoking
    0.50
    AddHtmlAttribute
    0.50
     Bioaccumulative
    0.50
     mengenakan
    0.49
     Zjednoc
    0.49
     rospy
    0.49
     Hibernate
    0.49
    Activations Density 0.010%

    No Known Activations