© 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. 4-CLT-HP
    7. 419
    Prev
    Next
    INDEX
    Explanations

    alo

    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
     виправивши
    -0.68
     Theſe
    -0.64
     suivants
    -0.60
    IBOutlet
    -0.59
    AutoScaleMode
    -0.58
     initComponents
    -0.58
     Organisation
    -0.57
     Fara
    -0.57
    ibouti
    -0.56
     indisponible
    -0.56
    POSITIVE LOGITS
    modelBuilder
    0.55
    andReturn
    0.52
     comparison
    0.42
    ny
    0.41
    rom
    0.40
    marginVertical
    0.40
    Rptr
    0.39
    ViewImports
    0.38
     comp
    0.38
    ning
    0.38
    Activations Density 0.004%

    No Known Activations