© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74951
    Prev
    Next
    INDEX
    Explanations

    in

    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
    EndInit
    -0.57
     Pingback
    -0.57
     tartalomajánló
    -0.55
    SequentialGroup
    -0.53
    featureID
    -0.51
    BrowserModule
    -0.50
    providedIn
    -0.50
    Skocz
    -0.47
    ather
    -0.46
    Spéc
    -0.46
    POSITIVE LOGITS
    <bos>
    0.56
     AspNetCore
    0.55
    kháu
    0.52
    AndroidJUnit
    0.52
     prêtres
    0.52
     CYTHON
    0.49
     noires
    0.47
     cases
    0.46
     otomatig
    0.46
     racines
    0.46
    Activations Density 0.004%

    No Known Activations