© 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. 43091
    Prev
    Next
    INDEX
    Explanations

    location references

    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
     MPH
    -1.24
    MPH
    -0.94
     Económica
    -0.86
    +#+#
    -0.82
     незавершена
    -0.81
     INTERESAR
    -0.77
     FetchType
    -0.77
    ftagPool
    -0.77
    +:+
    -0.77
     telegraph
    -0.74
    POSITIVE LOGITS
    át
    0.49
    ion
    0.49
    ante
    0.48
    me
    0.43
    mes
    0.43
     extra
    0.43
    ard
    0.42
    lund
    0.42
    ide
    0.41
    ando
    0.41
    Activations Density 0.033%

    No Known Activations