© 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. 92532
    Prev
    Next
    INDEX
    Explanations

    umi

    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
    zeiti
    -0.40
     vérit
    -0.40
    erweise
    -0.39
     Tl
    -0.39
    antry
    -0.38
    FieldNumber
    -0.37
    Földrajzportál
    -0.37
     Afr
    -0.36
     Derfor
    -0.36
    kloped
    -0.36
    POSITIVE LOGITS
     doInBackground
    0.67
    bap
    0.59
    abstractmethod
    0.57
    জ
    0.56
    цездатний
    0.55
     bangs
    0.54
     Inflate
    0.54
    bon
    0.54
     assuming
    0.53
     démo
    0.53
    Activations Density 0.000%

    No Known Activations