© 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. 98084
    Prev
    Next
    INDEX
    Explanations

    Transitions and movement

    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
     gezet
    -0.58
    ⓧ
    -0.55
     CanadaChoose
    -0.55
    Krok
    -0.54
     AssemblyVersion
    -0.53
     Pot
    -0.50
    yok
    -0.50
     mémor
    -0.50
     {?
    -0.49
     '\\;'
    -0.49
    POSITIVE LOGITS
    queryInterface
    0.63
     doInBackground
    0.56
     protoimpl
    0.56
     referrerpolicy
    0.56
    Istorija
    0.51
    LookAnd
    0.51
     sleeping
    0.49
     bed
    0.49
     far
    0.47
     mix
    0.47
    Activations Density 0.002%

    No Known Activations