© 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. 4-CLT-HP
    7. 1759
    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
    .
    -0.81
     []:
    -0.71
    .<
    -0.62
    .';
    -0.59
    providedIn
    -0.57
    not
    -0.55
    DOCTYPE
    -0.54
    Obrázky
    -0.53
    ."""
    -0.52
    .«
    -0.52
    POSITIVE LOGITS
    IUrlHelper
    0.71
    Spoljašnje
    0.65
     THOSE
    0.57
     the
    0.55
    marshaller
    0.54
     THAT
    0.54
    iedenen
    0.52
     hende
    0.52
    corbic
    0.51
    reggio
    0.51
    Activations Density 0.007%

    No Known Activations