© 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. 20-CLT-HP
    7. 73745
    Prev
    Next
    INDEX
    Explanations

    Code and internet language

    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
     propOrder
    -0.92
    OGND
    -0.83
    EndInit
    -0.77
    StoryboardSegue
    -0.74
    NewGuid
    -0.69
     createSlice
    -0.65
    WaitGroup
    -0.65
    Personendaten
    -0.65
     doigts
    -0.64
    iddhar
    -0.63
    POSITIVE LOGITS
     nakalista
    0.45
     AU
    0.43
     aus
    0.43
     lasting
    0.41
    يلات
    0.41
     out
    0.41
    ifrance
    0.40
     made
    0.39
    anius
    0.39
    fø
    0.39
    Activations Density 0.001%

    No Known Activations