© 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. 14754
    Prev
    Next
    INDEX
    Explanations

    probabilities

    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
    eko
    -0.98
     probabilities
    -0.84
    yntaxException
    -0.64
    RegressionTest
    -0.60
     Monfieur
    -0.59
     يتيمه
    -0.59
    seamnă
    -0.58
    astéro
    -0.58
     deſt
    -0.58
    FunctionFlags
    -0.57
    POSITIVE LOGITS
     بيها
    0.54
     '{@
    0.48
    GenerationType
    0.47
    abbr
    0.46
    ValueStyle
    0.45
    formación
    0.44
     GenerationType
    0.44
     endfor
    0.44
    ACADEM
    0.44
    describing
    0.43
    Activations Density 0.027%

    No Known Activations