© 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. 1-CLT-HP
    7. 15001
    Prev
    Next
    INDEX
    Explanations

    availability

    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
     RSSSF
    -0.57
    zusetzen
    -0.49
    StoryboardSegue
    -0.49
    ModelMap
    -0.48
    letzt
    -0.48
    хьтан
    -0.47
     UnityEditor
    -0.46
    Marry
    -0.46
    ChildScrollView
    -0.46
     энциклопедия
    -0.46
    POSITIVE LOGITS
     of
    0.69
     initComponents
    0.59
     חיצוניים
    0.58
     pocket
    0.55
    GraphicsUnit
    0.52
    pocket
    0.52
    ülle
    0.52
    ientôt
    0.51
     SqlDbType
    0.51
    irtschaft
    0.51
    Activations Density 0.010%

    No Known Activations