© 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. 0-CLT-HP
    7. 42561
    Prev
    Next
    INDEX
    Explanations

    impractical, ironically

    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
    findpost
    -0.81
     AssemblyProduct
    -0.70
     Meksiku
    -0.67
    zzleHttp
    -0.64
    GOTREF
    -0.64
     actionMode
    -0.64
    bParam
    -0.63
    цезда
    -0.63
    <bos>
    -0.62
    abestanden
    -0.61
    POSITIVE LOGITS
    ers
    0.51
    else
    0.50
    ly
    0.50
    ertos
    0.47
    elt
    0.46
    als
    0.46
    ally
    0.44
    lib
    0.43
     مشين
    0.41
    が
    0.41
    Activations Density 0.217%

    No Known Activations