© 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. 0-CLT-HP
    7. 43246
    Prev
    Next
    INDEX
    Explanations

    carcin or counter

    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
     Allen
    -0.73
     counter
    -0.69
    Allen
    -0.63
    ed
    -0.53
     à
    -0.53
     input
    -0.52
    ing
    -0.51
    er
    -0.51
     ass
    -0.50
     ad
    -0.50
    POSITIVE LOGITS
     Efq
    0.70
    Datuak
    0.69
     betweenstory
    0.69
     Monfieur
    0.69
     Charg
    0.68
     متعلقه
    0.68
     الحره
    0.67
     anhänger
    0.67
    XmlEnum
    0.67
     auffi
    0.67
    Activations Density 0.134%

    No Known Activations