© 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. 5442
    Prev
    Next
    INDEX
    Explanations

    anyak

    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
    VIAF
    -0.56
    mitives
    -0.51
    REP
    -0.51
    ewe
    -0.50
    cuerdo
    -0.50
    endientes
    -0.50
    brainly
    -0.50
    jedno
    -0.50
    SCR
    -0.49
     remittances
    -0.49
    POSITIVE LOGITS
    ba
    0.72
    WaitGroup
    0.53
    DataURL
    0.49
    Ba
    0.44
     Kata
    0.44
    PerformLayout
    0.43
    BA
    0.43
    bas
    0.43
    %;
    0.43
     Ba
    0.42
    Activations Density 0.001%

    No Known Activations