© 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. 4819
    Prev
    Next
    INDEX
    Explanations

    organizations

    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
    avadoc
    -0.50
    inematics
    -0.43
     pihak
    -0.42
    ()<<
    -0.41
    Nationalité
    -0.40
    MethodManager
    -0.39
    cepción
    -0.39
    JoinColumn
    -0.39
    ivir
    -0.38
    üyada
    -0.38
    POSITIVE LOGITS
     Efq
    0.69
    typeorm
    0.69
    DebuggerNonUser
    0.65
     beſt
    0.65
    ſelf
    0.64
     myſelf
    0.64
     <=",
    0.62
     ſame
    0.62
    thenReturn
    0.61
    derry
    0.60
    Activations Density 0.040%

    No Known Activations