© 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. 5-CLT-HP
    7. 96893
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings

    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
     ttc
    -0.52
     lh
    -0.48
    ReusableCell
    -0.48
    CDs
    -0.47
    SequentialGroup
    -0.46
     UD
    -0.45
     LF
    -0.45
    LF
    -0.45
     TextAppearance
    -0.44
     yeti
    -0.44
    POSITIVE LOGITS
    HandlerContext
    0.73
    VII
    0.66
    VIII
    0.65
    vii
    0.65
     Exactos
    0.61
     stratég
    0.61
    saraba
    0.60
     <=",
    0.60
    III
    0.59
    vog
    0.59
    Activations Density 0.001%

    No Known Activations