© 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. 5-CLT-HP
    7. 92777
    Prev
    Next
    INDEX
    Explanations

    not

    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
    SourceChecksum
    -0.75
    verwijspagina
    -0.59
    pulumi
    -0.58
    __":
    -0.57
    Bronnen
    -0.57
    ⎤
    -0.57
     autorytatywna
    -0.56
     AssemblyVersion
    -0.55
    ConfigureAwait
    -0.54
    +#+#
    -0.53
    POSITIVE LOGITS
     be
    0.86
     have
    0.85
     worry
    0.82
     let
    0.73
     waste
    0.70
     leave
    0.69
     expect
    0.69
     feel
    0.68
     allow
    0.68
     arrivo
    0.66
    Activations Density 0.002%

    No Known Activations