© 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. 1-CLT-HP
    7. 10377
    Prev
    Next
    INDEX
    Explanations

    liquef

    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
    Naissance
    -0.56
    ReusableCell
    -0.54
    UNTIME
    -0.53
     cors
    -0.52
     Réponses
    -0.52
    lesse
    -0.52
    setVerticalGroup
    -0.51
    LayoutPanel
    -0.50
     escalation
    -0.50
     mira
    -0.49
    POSITIVE LOGITS
    
    0.57
     giapp
    0.50
     SearchView
    0.49
    сылкі
    0.48
    extendable
    0.47
     الدولى
    0.47
     judiciaire
    0.45
     câte
    0.45
    igas
    0.44
     Может
    0.44
    Activations Density 0.003%

    No Known Activations