© 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. 77060
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ately or -ATE"

    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
    kund
    -0.49
     IMPLIED
    -0.47
    ccp
    -0.46
    CCP
    -0.46
    UnsafeEnabled
    -0.44
    IEU
    -0.43
    GED
    -0.43
    FieldDescriptor
    -0.42
     Ried
    -0.42
    ENED
    -0.42
    POSITIVE LOGITS
    ate
    0.91
    rate
    0.84
    ates
    0.81
     ate
    0.81
    atel
    0.75
    ATE
    0.75
    alte
    0.75
    nate
    0.72
    الإنجليزية
    0.70
    ately
    0.70
    Activations Density 0.015%

    No Known Activations