© 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. 77221
    Prev
    Next
    INDEX
    Explanations

    General conversational text

    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
    SharedDtor
    -0.80
    rrggbb
    -0.79
    Begriffsklä
    -0.73
    TintMode
    -0.68
    Vidite
    -0.66
    UnusedPrivate
    -0.66
    Personendaten
    -0.66
     typelib
    -0.64
    iredo
    -0.64
    autorest
    -0.63
    POSITIVE LOGITS
     hard
    0.69
     time
    0.55
    hard
    0.47
     and
    0.43
     she
    0.41
    Hard
    0.40
    HARD
    0.40
    time
    0.38
     harde
    0.38
     المعيارى
    0.36
    Activations Density 0.002%

    No Known Activations