© 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. 71799
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    IonicModule
    -0.59
     CURIAM
    -0.54
     ***!
    -0.50
     Schindler
    -0.46
    Referencie
    -0.44
     InkWell
    -0.43
    ティア
    -0.42
     AssemblyTitle
    -0.42
    uidado
    -0.41
     virtue
    -0.41
    POSITIVE LOGITS
    
    0.68
    SequentialGroup
    0.60
    istan
    0.59
    躇
    0.59
    AVAN
    0.56
    CloseOperation
    0.55
     OMITBAD
    0.54
    mitian
    0.52
     MethodInfo
    0.52
     εγ
    0.51
    Activations Density 0.004%

    No Known Activations