© 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. 10438
    Prev
    Next
    INDEX
    Explanations

    bad

    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
     nakalista
    -0.67
    WithIOException
    -0.63
    PhysRevLett
    -0.62
    PhysRev
    -0.60
     Enquiry
    -0.60
    quiry
    -0.59
    gypti
    -0.59
    otomy
    -0.59
    Portale
    -0.58
    elemField
    -0.58
    POSITIVE LOGITS
    dies
    0.61
    s
    0.57
    vertising
    0.51
     bra
    0.50
    die
    0.47
    das
    0.45
    hasErrors
    0.44
    principalTable
    0.42
     school
    0.42
    Base
    0.41
    Activations Density 0.003%

    No Known Activations