© 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. 4650
    Prev
    Next
    INDEX
    Explanations

    in

    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
    my
    -0.51
     surla
    -0.48
    rifugal
    -0.48
     ketahui
    -0.47
    obut
    -0.47
     bienven
    -0.47
     obrig
    -0.47
    ljiv
    -0.46
    ndez
    -0.46
    kyou
    -0.46
    POSITIVE LOGITS
     essence
    0.77
     effect
    0.68
    writeFieldEnd
    0.66
    RegressionTest
    0.64
    ConstraintMaker
    0.60
    Referencies
    0.59
    DockStyle
    0.59
    mates
    0.59
     fhort
    0.58
    Rhestr
    0.57
    Activations Density 0.002%

    No Known Activations