© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1571
    Prev
    Next
    INDEX
    Explanations

    Short names

    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
    IntoConstraints
    -0.54
     autorytatywna
    -0.48
    Rüyada
    -0.48
    BindingResult
    -0.46
     StringTokenizer
    -0.45
    VolleyError
    -0.45
    providedIn
    -0.44
    XtraEditors
    -0.44
    ExecuteReader
    -0.44
    DataContract
    -0.43
    POSITIVE LOGITS
    AutoScaleMode
    0.59
     ujednoznacz
    0.55
    vermögen
    0.54
    PreferredItem
    0.53
    
    0.52
     mourut
    0.50
     dépass
    0.49
     تضيفلها
    0.49
    maxx
    0.48
     Throwable
    0.48
    Activations Density 0.009%

    No Known Activations