© 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. 77264
    Prev
    Next
    INDEX
    Explanations

    Code/formal documents

    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
     hauts
    -0.46
    ticale
    -0.45
    form
    -0.45
     der
    -0.44
     gainera
    -0.43
     nostru
    -0.43
    idjan
    -0.43
    jetunion
    -0.43
     cap
    -0.43
    ban
    -0.43
    POSITIVE LOGITS
    HostException
    0.88
    UnsafeEnabled
    0.82
    StoryboardSegue
    0.78
     виправивши
    0.75
     تانيه
    0.74
    setupUi
    0.72
    ReusableCell
    0.71
    Przypisy
    0.70
     незавершена
    0.68
    ChildScrollView
    0.68
    Activations Density 0.000%

    No Known Activations