© 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. 20-CLT-HP
    7. 72300
    Prev
    Next
    INDEX
    Explanations

    Code, technical reports

    np_max-act-logits · 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
    AndEndTag
    -0.69
    mobileqq
    -0.56
    prefixer
    -0.55
    NewUrlParser
    -0.54
    awtextra
    -0.52
    oughly
    -0.51
     posteriore
    -0.51
    IntoConstraints
    -0.50
    Билгалдахарш
    -0.49
    httphttps
    -0.49
    POSITIVE LOGITS
    ArgsConstructor
    0.54
    igshid
    0.52
    f
    0.51
    fml
    0.50
     vittoria
    0.49
    ms
    0.48
    MTT
    0.47
    nestjs
    0.47
     fVar
    0.45
    Datuak
    0.45
    Activations Density 0.005%

    No Known Activations