© 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. 20
    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
    MigrationBuilder
    -0.84
    Portale
    -0.78
    StructEnd
    -0.75
     Савезне
    -0.74
     esternos
    -0.73
    KommentareTeilen
    -0.70
    NameInMap
    -0.70
    Portail
    -0.68
     Walkover
    -0.68
     vérit
    -0.65
    POSITIVE LOGITS
     woods
    0.52
     land
    0.52
     open
    0.51
     gun
    0.50
     forest
    0.49
     sword
    0.49
     mind
    0.45
    landt
    0.45
     fly
    0.45
     Veld
    0.44
    Activations Density 0.002%

    No Known Activations