© 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. 5-CLT-HP
    7. 3752
    Prev
    Next
    INDEX
    Explanations

    slit

    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
     Niv
    -0.43
     ویکی‌پدیا
    -0.42
    writeFieldEnd
    -0.42
    Brainz
    -0.42
     Vikipedi
    -0.42
     tartalomajánló
    -0.41
    itively
    -0.40
    OnAdd
    -0.40
     CRES
    -0.40
    calciatore
    -0.39
    POSITIVE LOGITS
    
    0.77
    Geplaatst
    0.76
    expandindo
    0.73
     lamp
    0.68
    lamp
    0.65
     Lamp
    0.63
    脚注の使い方
    0.61
    Lamp
    0.59
     lamps
    0.55
    TYPED
    0.54
    Activations Density 0.000%

    No Known Activations