© 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. 20-CLT-HP
    7. 71699
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · 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
    دانشنامهٔ
    -0.66
    Geplaatst
    -0.65
    UpInside
    -0.60
    SharedCtor
    -0.57
     noDo
    -0.57
    astéroïdes
    -0.57
    GIVEREF
    -0.56
     estekak
    -0.56
    OGND
    -0.55
    ")));
    -0.53
    POSITIVE LOGITS
     the
    0.68
    extAlignment
    0.59
     a
    0.54
    ArgsConstructor
    0.54
    Attached
    0.48
    âmara
    0.47
    kje
    0.45
     Somerset
    0.45
    麼
    0.44
    openzeppelin
    0.44
    Activations Density 0.000%

    No Known Activations