© 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. 0-CLT-HP
    7. 92819
    Prev
    Next
    INDEX
    Explanations

    buy

    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
    InputBorder
    -0.59
    AndEndTag
    -0.57
     manqué
    -0.57
     trabalhando
    -0.56
     désormais
    -0.54
    IVEREF
    -0.53
    interopRequire
    -0.52
     TextAppearance
    -0.52
    Notae
    -0.50
    speaking
    -0.50
    POSITIVE LOGITS
     their
    0.63
     the
    0.60
     it
    0.59
     bread
    0.57
    stens
    0.54
     his
    0.51
    LookAnd
    0.49
    delli
    0.48
    Према
    0.48
    isserie
    0.47
    Activations Density 0.032%

    No Known Activations