© 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. 91710
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Chwiliwch
    -0.71
     estimés
    -0.70
    Abitanti
    -0.63
    ApiModelProperty
    -0.58
     تضيفلها
    -0.57
    +/**
    -0.56
    ModelSerializer
    -0.55
     initComponents
    -0.54
     Савезне
    -0.53
    fromnode
    -0.52
    POSITIVE LOGITS
     it
    0.74
     the
    0.67
     an
    0.54
     a
    0.52
    ngOnInit
    0.50
     tå
    0.46
     there
    0.45
    Número
    0.45
     graisse
    0.45
     Siria
    0.45
    Activations Density 0.001%

    No Known Activations