© 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. 77031
    Prev
    Next
    INDEX
    Explanations

    Document beginnings

    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
     kasarigan
    -1.00
     '\\;'
    -0.90
    Personendaten
    -0.87
     autorytatywna
    -0.71
     distanciation
    -0.70
    AnimationsModule
    -0.69
    VIAF
    -0.69
    MLLoader
    -0.68
     referenties
    -0.68
    Coordonnées
    -0.68
    POSITIVE LOGITS
    usion
    0.41
    Mute
    0.40
    Block
    0.40
    нке
    0.40
    JsonPropertyName
    0.39
    V
    0.39
     V
    0.38
    bo
    0.37
    eroll
    0.37
     seat
    0.37
    Activations Density 0.000%

    No Known Activations