© 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. 1062
    Prev
    Next
    INDEX
    Explanations

    admission

    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
    LLocation
    -0.52
    icals
    -0.48
    hical
    -0.47
    newArrayList
    -0.47
    AutoField
    -0.47
    ագրություններ
    -0.47
     strop
    -0.47
    ipat
    -0.47
    ligators
    -0.47
    theory
    -0.45
    POSITIVE LOGITS
    #+#
    0.59
     counselors
    0.57
    oa̍t
    0.56
    PerformLayout
    0.55
     counselor
    0.55
    MigrationBuilder
    0.55
     Counselor
    0.53
    findpost
    0.52
    
    0.52
     Palatine
    0.51
    Activations Density 0.003%

    No Known Activations