© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72052
    Prev
    Next
    INDEX
    Explanations

    Technical excerpts

    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
     ä
    -0.51
    viewDidLoad
    -0.50
    
    -0.49
    fromCharCode
    -0.46
    [::-
    -0.44
    JSONException
    -0.43
     banner
    -0.43
    Thunk
    -0.43
    함
    -0.42
    Erreferentziak
    -0.41
    POSITIVE LOGITS
    SharedDtor
    0.70
     doInBackground
    0.69
     igenom
    0.56
     pancre
    0.55
     Myron
    0.54
     varandra
    0.54
    neiden
    0.54
    MSD
    0.53
     OnTriggerEnter
    0.52
    ConstraintMaker
    0.52
    Activations Density 0.002%

    No Known Activations