© 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. 20-CLT-HP
    7. 76646
    Prev
    Next
    INDEX
    Explanations

    Company legal names

    np_max-act-logits · 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
     INC
    -0.78
     Inc
    -0.73
     CORPORATION
    -0.73
     Corp
    -0.71
    calientes
    -0.71
     CORP
    -0.70
    msgTypes
    -0.68
    Corp
    -0.68
    évaluateur
    -0.67
     LLC
    -0.66
    POSITIVE LOGITS
     Lid
    0.75
     Lim
    0.59
    Lid
    0.55
    enumi
    0.49
     LID
    0.47
    ITED
    0.47
     Lil
    0.42
    LID
    0.42
     MediatR
    0.42
    ิม
    0.42
    Activations Density 0.002%

    No Known Activations